The following is an instance of a README file that allows the others to understand this data structure, some properties and re-run data pre-processing, training, validation and evaluation.
Download data (and move into project folder): https://www.kaggle.com/datasets/andradaolteanu/gtzan-dataset-music-genre-classification
At first, you have to "pip install" all the required packages in requirements.txt file. I run my code on the Pycharm(community version), and I use the tensorflow-gpu package which means the whole process will be executed on the GPU (if GPU is not available, it will implement on the CPU). However running on the GPU it requires a lot of configuration work.
python3.6.0/ keras2.3.1/ tensorflow-gpu2.0.0/ CUDA10.0.0/ cuDNN7.6.0.64 for CUDA10.0
You have to strictly follow the correct version about five above package since there are bound relationship between them.
The CUDA installation package, cuDNN files and tensorflow whl file can be find in the directory of venv_python3.6 .
If you want to run code in the terminal of Pycharm:
You have to install CUDA first.
After CUDA installatoion, you need to unzip cuDNN file and remove its file of each directory into corresponding directory of "NVIDIA GPU Computing Toolkit\CUDA\v10.0".
Execute nvcc -V on your terminal. If successful, the cuda version number will be returned.
If you want to run code in the jupyter notebook:
You have to use "pip install tensorflow_gpu-2.0.0-cp36-cp36m-win_amd64.whl",
"conda install cudatoolkit=10.0"
and "conda install cudnn"
Comp47650_Yinjie_Liu_20211091
-checkpoints
|
----> cnn1
----> fcnn1
----> fcnn2
- Data
|
---> features_3_sec.csv
---> features_30_sec.csv
---> test.csv
---> train.csv
---> val.csv
---> cnn1_json
|
===> data_10.json
---> genres_original
|
===> blues
.
.
.
===> rock
---> images_original
|
===> blues
.
.
.
===> rock
- figs
|
---> cnn1_training_vis.png
---> fcnn1_training_vis.png
---> fcnn2_training_vis.png
---> PCA_Scattert.png
- logs
|
---> cnn1
|
---> CNN1_040422_232546.json
---> fcnn1
|
---> FCNN1_050422_202621.json
---> fcnn2
|
---> FCNN2_050422_203047.json
- models
|
---->__pycache__
|
---> cnn1.cpython-36.pyc
---> fcnn1.cpython-36.pyc
---> fcnn2.cpython-36.pyc
----> cnn1.py
----> fcnn1.py
----> fcnn2.py
- utils
|
---->__pycache__
|
---> cnn1.cpython-36.pyc
---> fcnn1.cpython-36.pyc
---> fcnn2.cpython-36.pyc
---> Datasets.py
---> params.py
---> plotting.py
hparams.yaml
main.py
README.html
README.ipynb
requirements.txt
At the beginning of the work, I chose to analse this data in detail. Showing the structure of features_3_sec.csv file and there are 57 properties inside of this data. And then I picked one of them to show its Zoomed audio wave graph, Simple audio waveplot and Principal component analysis on Music Genres graph amongest ten different labels.
import numpy as np
import pandas as pd
import json
import librosa
from IPython.display import Audio
import librosa.display as lplt
import matplotlib.pyplot as plt
from sklearn.decomposition import PCA
import sklearn.preprocessing as skp
import seaborn as sns
sns.set_style('whitegrid')
%matplotlib inline
df = pd.read_csv('Data/features_3_sec.csv')
df.head()
| filename | length | chroma_stft_mean | chroma_stft_var | rms_mean | rms_var | spectral_centroid_mean | spectral_centroid_var | spectral_bandwidth_mean | spectral_bandwidth_var | ... | mfcc16_var | mfcc17_mean | mfcc17_var | mfcc18_mean | mfcc18_var | mfcc19_mean | mfcc19_var | mfcc20_mean | mfcc20_var | label | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | blues.00000.0.wav | 66149 | 0.335406 | 0.091048 | 0.130405 | 0.003521 | 1773.065032 | 167541.630869 | 1972.744388 | 117335.771563 | ... | 39.687145 | -3.241280 | 36.488243 | 0.722209 | 38.099152 | -5.050335 | 33.618073 | -0.243027 | 43.771767 | blues |
| 1 | blues.00000.1.wav | 66149 | 0.343065 | 0.086147 | 0.112699 | 0.001450 | 1816.693777 | 90525.690866 | 2010.051501 | 65671.875673 | ... | 64.748276 | -6.055294 | 40.677654 | 0.159015 | 51.264091 | -2.837699 | 97.030830 | 5.784063 | 59.943081 | blues |
| 2 | blues.00000.2.wav | 66149 | 0.346815 | 0.092243 | 0.132003 | 0.004620 | 1788.539719 | 111407.437613 | 2084.565132 | 75124.921716 | ... | 67.336563 | -1.768610 | 28.348579 | 2.378768 | 45.717648 | -1.938424 | 53.050835 | 2.517375 | 33.105122 | blues |
| 3 | blues.00000.3.wav | 66149 | 0.363639 | 0.086856 | 0.132565 | 0.002448 | 1655.289045 | 111952.284517 | 1960.039988 | 82913.639269 | ... | 47.739452 | -3.841155 | 28.337118 | 1.218588 | 34.770935 | -3.580352 | 50.836224 | 3.630866 | 32.023678 | blues |
| 4 | blues.00000.4.wav | 66149 | 0.335579 | 0.088129 | 0.143289 | 0.001701 | 1630.656199 | 79667.267654 | 1948.503884 | 60204.020268 | ... | 30.336359 | 0.664582 | 45.880913 | 1.689446 | 51.363583 | -3.392489 | 26.738789 | 0.536961 | 29.146694 | blues |
5 rows × 60 columns
print("As for this Dataset's structure, there are {row} rows and {column} columns".format(row=df.shape[0], column=df.shape[1]))
As for this Dataset's structure, there are 9990 rows and 60 columns
df.label.value_counts().reset_index()
| index | label | |
|---|---|---|
| 0 | reggae | 1000 |
| 1 | pop | 1000 |
| 2 | metal | 1000 |
| 3 | jazz | 1000 |
| 4 | blues | 1000 |
| 5 | disco | 999 |
| 6 | rock | 998 |
| 7 | hiphop | 998 |
| 8 | classical | 998 |
| 9 | country | 997 |
audio_simple = 'Data/genres_original/hiphop/hiphop.00099.wav'
audio_data, sample_rate = librosa.load(audio_simple)
audio_data, _ = librosa.effects.trim(audio_data)
# play sample file
Audio(audio_data, rate=sample_rate)
start = 2000
end = 5000
plt.figure(figsize=(14,4))
plt.title("Zoomed audio wave ",fontsize=15)
plt.plot(audio_data[start:end])
plt.grid()
plt.show()
plt.figure(figsize=(14, 4))
plt.title("Simple audio waveplot ",fontsize=15)
plt.grid()
lplt.waveshow(audio_data, sr=sample_rate)
plt.show()
# Principal component analysis
data = df.iloc[0:, 1:]
y = data['label']
X = data.loc[:, data.columns != 'label']
# normalize the data
cols = X.columns
min_max_scaler = skp.MinMaxScaler()
np_scaled = min_max_scaler.fit_transform(X)
X = pd.DataFrame(np_scaled, columns = cols)
# find top 2 pca components
pca = PCA(n_components=2)
principalComponents = pca.fit_transform(X)
principalDf = pd.DataFrame(data = principalComponents, columns = ['pc1', 'pc2'])
# connect with target label
finalDf = pd.concat([principalDf, y], axis = 1)
plt.figure(figsize = (17, 10))
sns.scatterplot(x = "pc1", y = "pc2", data = finalDf, hue = "label", alpha = 0.7, s = 100);
plt.title('Principal component analysis on Music Genres', fontsize = 15)
plt.xticks(fontsize = 11)
plt.yticks(fontsize = 17);
plt.xlabel("The first Principal Component", fontsize = 15)
plt.ylabel("The second Principal Component", fontsize = 15)
plt.savefig("figs/PCA_Scattert.png")
# There is no missing values in the features_3_sec.csv file.
print("Columns with NA values are",list(df.columns[df.isnull().any()]))
Columns with NA values are []
The CNN model firstly came to my mind, and I searched lots of materials how to process audio files.
The librosa package can be used to extract the mcff attribute of a audio file.
And I saved them in the Data/cnn1_json/data_10.json file which includes each audio file mcff data, its label and each label's directory.
And I used keras to implement a CNN network to train, and its compile parameters can be found in the hparams.yaml file.
You can run the "python main.py CNN1 --write_data True" in the terminal of Pycharm.(Warning: the right Virtual environment should be venv_python3.6)
Or you can directly run ! python main.py CNN1 --write_data True in the jupyter notebook
! python main.py CNN1 --write_data True
F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00000.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00000.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00000.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00000.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00000.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00000.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00001.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00001.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00001.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00001.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00001.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00001.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00002.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00002.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00002.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00002.wav, segment:4
2022-04-11 23:05:53.794042: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll 2022-04-11 23:08:20.828381: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 2022-04-11 23:08:20.833366: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll 2022-04-11 23:08:21.802996: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:08:21.803032: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:08:21.808235: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:08:22.477409: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:08:22.477429: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:08:22.477434: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:08:22.484948: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) WARNING:tensorflow:From D:\Programs\Anaconda_app\envs\comp47650_env\lib\site-packages\tensorflow_core\python\ops\resource_variable_ops.py:1630: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version. Instructions for updating: If using Keras pass *_constraint arguments to layers. 2022-04-11 23:08:22.580814: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00002.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00002.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00003.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00003.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00003.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00003.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00003.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00003.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00004.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00004.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00004.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00004.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00004.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00004.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00005.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00005.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00005.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00005.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00005.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00005.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00006.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00006.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00006.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00006.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00006.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00006.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00007.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00007.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00007.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00007.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00007.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00007.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00008.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00008.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00008.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00008.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00008.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00008.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00009.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00009.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00009.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00009.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00009.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00009.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00010.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00010.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00010.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00010.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00010.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00010.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00011.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00011.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00011.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00011.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00011.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00011.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00012.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00012.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00012.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00012.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00012.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00012.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00013.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00013.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00013.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00013.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00013.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00013.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00014.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00014.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00014.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00014.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00014.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00014.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00015.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00015.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00015.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00015.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00015.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00015.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00016.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00016.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00016.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00016.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00016.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00016.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00017.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00017.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00017.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00017.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00017.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00017.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00018.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00018.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00018.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00018.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00018.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00018.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00019.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00019.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00019.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00019.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00019.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00019.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00020.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00020.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00020.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00020.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00020.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00020.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00021.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00021.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00021.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00021.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00021.wav, segment:5
name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:08:22.580836: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:08:22.585952: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:08:24.104607: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll 2022-04-11 23:08:24.358006: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll 2022-04-11 23:08:25.300694: W tensorflow/stream_executor/cuda/redzone_allocator.cc:312] Internal: Invoking ptxas not supported on Windows Relying on driver to perform ptx compilation. This message will be only logged once. 2022-04-11 23:09:22.000737: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:09:22.000763: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:09:22.007941: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:09:22.008020: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:09:22.008031: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:09:22.008038: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:09:22.014203: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) 2022-04-11 23:09:23.221591: W tensorflow/python/util/util.cc:299] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them.
F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00021.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00022.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00022.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00022.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00022.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00022.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00022.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00023.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00023.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00023.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00023.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00023.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00023.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00024.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00024.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00024.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00024.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00024.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00024.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00025.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00025.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00025.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00025.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00025.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00025.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00026.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00026.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00026.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00026.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00026.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00026.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00027.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00027.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00027.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00027.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00027.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00027.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00028.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00028.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00028.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00028.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00028.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00028.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00029.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00029.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00029.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00029.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00029.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00029.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00030.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00030.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00030.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00030.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00030.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00030.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00031.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00031.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00031.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00031.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00031.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00031.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00032.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00032.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00032.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00032.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00032.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00032.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00033.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00033.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00033.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00033.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00033.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00033.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00034.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00034.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00034.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00034.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00034.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00034.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00035.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00035.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00035.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00035.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00035.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00035.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00036.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00036.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00036.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00036.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00036.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00036.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00037.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00037.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00037.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00037.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00037.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00037.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00038.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00038.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00038.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00038.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00038.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00038.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00039.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00039.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00039.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00039.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00039.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00039.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00040.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00040.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00040.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00040.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00040.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00040.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00041.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00041.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00041.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00041.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00041.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00041.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00042.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00042.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00042.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00042.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00042.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00042.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00043.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00043.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00043.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00043.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00043.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00043.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00044.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00044.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00044.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00044.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00044.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00044.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00045.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00045.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00045.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00045.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00045.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00045.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00046.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00046.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00046.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00046.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00046.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00046.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00047.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00047.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00047.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00047.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00047.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00047.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00048.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00048.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00048.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00048.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00048.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00048.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00049.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00049.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00049.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00049.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00049.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00049.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00050.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00050.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00050.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00050.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00050.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00050.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00051.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00051.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00051.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00051.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00051.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00051.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00052.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00052.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00052.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00052.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00052.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00052.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00053.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00053.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00053.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00053.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00053.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00053.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00054.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00054.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00054.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00054.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00054.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00054.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00055.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00055.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00055.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00055.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00055.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00055.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00056.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00056.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00056.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00056.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00056.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00056.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00057.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00057.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00057.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00057.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00057.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00057.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00058.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00058.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00058.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00058.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00058.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00058.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00059.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00059.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00059.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00059.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00059.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00059.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00060.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00060.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00060.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00060.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00060.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00060.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00061.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00061.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00061.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00061.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00061.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00061.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00062.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00062.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00062.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00062.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00062.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00062.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00063.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00063.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00063.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00063.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00063.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00063.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00064.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00064.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00064.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00064.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00064.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00064.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00065.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00065.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00065.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00065.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00065.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00065.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00066.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00066.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00066.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00066.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00066.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00066.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00067.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00067.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00067.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00067.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00067.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00067.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00068.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00068.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00068.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00068.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00068.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00068.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00069.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00069.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00069.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00069.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00069.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00069.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00070.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00070.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00070.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00070.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00070.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00070.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00071.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00071.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00071.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00071.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00071.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00071.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00072.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00072.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00072.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00072.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00072.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00072.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00073.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00073.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00073.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00073.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00073.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00073.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00074.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00074.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00074.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00074.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00074.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00074.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00075.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00075.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00075.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00075.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00075.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00075.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00076.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00076.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00076.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00076.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00076.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00076.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00077.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00077.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00077.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00077.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00077.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00077.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00078.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00078.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00078.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00078.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00078.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00078.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00079.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00079.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00079.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00079.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00079.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00079.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00080.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00080.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00080.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00080.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00080.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00080.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00081.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00081.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00081.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00081.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00081.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00081.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00082.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00082.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00082.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00082.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00082.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00082.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00083.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00083.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00083.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00083.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00083.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00083.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00084.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00084.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00084.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00084.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00084.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00084.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00085.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00085.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00085.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00085.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00085.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00085.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00086.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00086.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00086.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00086.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00086.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00086.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00087.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00087.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00087.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00087.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00087.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00087.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00088.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00088.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00088.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00088.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00088.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00088.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00089.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00089.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00089.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00089.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00089.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00089.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00090.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00090.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00090.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00090.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00090.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00090.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00091.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00091.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00091.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00091.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00091.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00091.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00092.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00092.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00092.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00092.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00092.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00092.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00093.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00093.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00093.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00093.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00093.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00093.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00094.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00094.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00094.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00094.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00094.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00094.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00095.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00095.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00095.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00095.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00095.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00095.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00096.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00096.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00096.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00096.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00096.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00096.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00097.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00097.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00097.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00097.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00097.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00097.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00098.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00098.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00098.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00098.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00098.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00098.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00099.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00099.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00099.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00099.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00099.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\blues\blues.00099.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00000.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00000.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00000.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00000.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00000.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00000.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00001.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00001.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00001.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00001.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00001.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00001.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00002.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00002.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00002.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00002.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00002.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00002.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00003.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00003.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00003.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00003.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00003.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00003.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00004.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00004.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00004.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00004.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00004.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00004.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00005.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00005.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00005.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00005.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00005.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00005.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00006.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00006.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00006.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00006.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00006.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00006.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00007.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00007.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00007.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00007.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00007.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00007.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00008.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00008.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00008.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00008.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00008.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00008.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00009.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00009.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00009.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00009.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00009.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00009.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00010.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00010.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00010.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00010.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00010.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00010.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00011.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00011.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00011.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00011.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00011.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00011.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00012.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00012.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00012.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00012.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00012.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00012.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00013.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00013.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00013.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00013.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00013.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00013.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00014.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00014.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00014.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00014.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00014.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00014.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00015.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00015.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00015.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00015.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00015.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00015.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00016.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00016.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00016.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00016.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00016.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00016.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00017.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00017.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00017.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00017.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00017.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00017.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00018.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00018.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00018.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00018.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00018.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00018.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00019.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00019.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00019.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00019.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00019.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00019.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00020.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00020.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00020.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00020.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00020.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00020.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00021.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00021.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00021.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00021.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00021.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00021.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00022.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00022.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00022.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00022.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00022.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00022.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00023.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00023.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00023.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00023.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00023.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00023.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00024.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00024.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00024.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00024.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00024.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00024.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00025.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00025.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00025.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00025.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00025.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00025.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00026.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00026.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00026.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00026.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00026.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00026.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00027.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00027.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00027.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00027.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00027.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00027.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00028.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00028.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00028.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00028.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00028.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00028.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00029.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00029.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00029.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00029.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00029.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00029.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00030.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00030.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00030.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00030.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00030.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00030.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00031.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00031.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00031.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00031.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00031.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00031.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00032.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00032.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00032.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00032.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00032.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00032.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00033.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00033.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00033.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00033.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00033.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00033.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00034.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00034.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00034.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00034.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00034.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00034.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00035.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00035.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00035.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00035.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00035.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00035.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00036.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00036.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00036.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00036.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00036.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00036.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00037.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00037.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00037.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00037.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00037.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00037.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00038.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00038.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00038.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00038.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00038.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00038.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00039.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00039.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00039.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00039.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00039.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00039.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00040.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00040.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00040.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00040.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00040.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00040.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00041.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00041.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00041.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00041.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00041.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00041.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00042.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00042.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00042.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00042.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00042.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00042.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00043.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00043.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00043.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00043.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00043.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00043.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00044.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00044.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00044.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00044.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00044.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00044.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00045.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00045.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00045.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00045.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00045.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00045.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00046.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00046.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00046.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00046.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00046.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00046.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00047.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00047.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00047.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00047.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00047.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00047.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00048.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00048.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00048.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00048.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00048.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00048.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00049.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00049.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00049.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00049.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00049.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00049.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00050.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00050.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00050.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00050.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00050.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00050.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00051.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00051.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00051.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00051.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00051.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00051.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00052.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00052.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00052.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00052.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00052.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00052.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00053.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00053.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00053.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00053.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00053.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00053.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00054.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00054.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00054.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00054.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00054.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00054.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00055.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00055.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00055.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00055.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00055.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00055.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00056.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00056.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00056.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00056.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00056.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00056.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00057.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00057.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00057.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00057.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00057.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00057.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00058.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00058.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00058.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00058.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00058.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00058.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00059.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00059.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00059.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00059.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00059.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00059.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00060.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00060.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00060.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00060.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00060.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00060.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00061.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00061.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00061.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00061.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00061.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00061.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00062.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00062.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00062.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00062.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00062.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00062.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00063.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00063.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00063.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00063.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00063.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00063.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00064.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00064.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00064.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00064.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00064.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00064.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00065.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00065.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00065.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00065.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00065.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00065.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00066.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00066.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00066.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00066.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00066.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00066.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00067.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00067.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00067.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00067.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00067.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00067.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00068.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00068.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00068.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00068.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00068.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00068.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00069.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00069.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00069.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00069.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00069.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00069.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00070.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00070.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00070.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00070.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00070.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00070.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00071.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00071.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00071.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00071.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00071.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00071.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00072.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00072.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00072.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00072.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00072.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00072.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00073.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00073.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00073.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00073.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00073.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00073.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00074.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00074.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00074.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00074.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00074.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00074.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00075.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00075.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00075.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00075.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00075.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00075.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00076.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00076.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00076.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00076.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00076.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00076.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00077.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00077.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00077.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00077.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00077.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00077.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00078.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00078.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00078.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00078.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00078.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00078.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00079.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00079.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00079.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00079.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00079.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00079.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00080.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00080.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00080.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00080.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00080.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00080.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00081.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00081.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00081.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00081.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00081.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00081.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00082.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00082.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00082.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00082.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00082.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00082.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00083.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00083.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00083.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00083.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00083.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00083.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00084.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00084.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00084.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00084.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00084.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00084.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00085.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00085.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00085.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00085.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00085.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00085.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00086.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00086.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00086.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00086.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00086.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00086.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00087.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00087.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00087.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00087.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00087.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00087.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00088.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00088.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00088.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00088.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00088.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00088.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00089.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00089.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00089.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00089.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00089.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00089.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00090.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00090.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00090.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00090.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00090.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00090.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00091.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00091.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00091.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00091.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00091.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00091.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00092.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00092.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00092.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00092.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00092.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00092.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00093.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00093.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00093.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00093.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00093.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00093.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00094.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00094.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00094.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00094.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00094.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00094.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00095.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00095.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00095.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00095.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00095.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00095.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00096.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00096.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00096.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00096.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00096.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00096.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00097.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00097.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00097.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00097.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00097.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00097.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00098.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00098.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00098.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00098.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00098.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00098.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00099.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00099.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00099.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00099.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00099.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\classical\classical.00099.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00000.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00000.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00000.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00000.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00000.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00000.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00001.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00001.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00001.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00001.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00001.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00001.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00002.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00002.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00002.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00002.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00002.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00002.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00003.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00003.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00003.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00003.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00003.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00003.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00004.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00004.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00004.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00004.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00004.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00004.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00005.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00005.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00005.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00005.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00005.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00005.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00006.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00006.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00006.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00006.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00006.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00006.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00007.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00007.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00007.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00007.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00007.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00008.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00008.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00008.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00008.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00008.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00008.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00009.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00009.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00009.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00009.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00009.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00009.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00010.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00010.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00010.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00010.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00010.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00010.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00011.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00011.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00011.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00011.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00011.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00011.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00012.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00012.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00012.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00012.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00012.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00012.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00013.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00013.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00013.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00013.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00013.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00013.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00014.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00014.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00014.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00014.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00014.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00014.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00015.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00015.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00015.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00015.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00015.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00015.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00016.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00016.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00016.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00016.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00016.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00016.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00017.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00017.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00017.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00017.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00017.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00017.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00018.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00018.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00018.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00018.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00018.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00018.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00019.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00019.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00019.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00019.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00019.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00019.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00020.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00020.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00020.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00020.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00020.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00020.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00021.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00021.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00021.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00021.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00021.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00021.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00022.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00022.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00022.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00022.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00022.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00022.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00023.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00023.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00023.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00023.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00023.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00023.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00024.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00024.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00024.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00024.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00024.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00024.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00025.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00025.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00025.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00025.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00025.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00025.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00026.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00026.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00026.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00026.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00026.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00026.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00027.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00027.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00027.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00027.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00027.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00027.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00028.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00028.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00028.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00028.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00028.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00028.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00029.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00029.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00029.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00029.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00029.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00029.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00030.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00030.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00030.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00030.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00030.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00030.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00031.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00031.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00031.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00031.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00031.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00031.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00032.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00032.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00032.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00032.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00032.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00032.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00033.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00033.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00033.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00033.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00033.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00033.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00034.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00034.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00034.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00034.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00034.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00034.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00035.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00035.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00035.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00035.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00035.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00035.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00036.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00036.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00036.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00036.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00036.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00036.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00037.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00037.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00037.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00037.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00037.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00037.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00038.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00038.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00038.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00038.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00038.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00038.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00039.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00039.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00039.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00039.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00039.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00039.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00040.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00040.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00040.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00040.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00040.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00040.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00041.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00041.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00041.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00041.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00041.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00041.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00042.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00042.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00042.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00042.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00042.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00042.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00043.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00043.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00043.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00043.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00043.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00043.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00044.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00044.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00044.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00044.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00044.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00044.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00045.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00045.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00045.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00045.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00045.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00045.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00046.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00046.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00046.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00046.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00046.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00046.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00047.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00047.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00047.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00047.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00047.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00047.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00048.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00048.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00048.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00048.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00048.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00048.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00049.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00049.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00049.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00049.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00049.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00049.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00050.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00050.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00050.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00050.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00050.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00050.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00051.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00051.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00051.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00051.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00051.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00051.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00052.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00052.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00052.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00052.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00052.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00052.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00053.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00053.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00053.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00053.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00053.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00053.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00054.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00054.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00054.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00054.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00054.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00054.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00055.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00055.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00055.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00055.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00055.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00055.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00056.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00056.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00056.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00056.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00056.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00056.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00057.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00057.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00057.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00057.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00057.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00057.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00058.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00058.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00058.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00058.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00058.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00058.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00059.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00059.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00059.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00059.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00059.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00059.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00060.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00060.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00060.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00060.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00060.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00060.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00061.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00061.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00061.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00061.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00061.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00061.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00062.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00062.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00062.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00062.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00062.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00062.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00063.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00063.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00063.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00063.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00063.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00063.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00064.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00064.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00064.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00064.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00064.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00064.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00065.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00065.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00065.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00065.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00065.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00065.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00066.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00066.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00066.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00066.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00066.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00066.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00067.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00067.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00067.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00067.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00067.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00067.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00068.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00068.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00068.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00068.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00068.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00068.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00069.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00069.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00069.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00069.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00069.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00069.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00070.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00070.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00070.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00070.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00070.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00070.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00071.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00071.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00071.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00071.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00071.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00071.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00072.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00072.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00072.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00072.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00072.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00072.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00073.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00073.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00073.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00073.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00073.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00073.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00074.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00074.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00074.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00074.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00074.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00074.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00075.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00075.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00075.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00075.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00075.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00075.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00076.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00076.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00076.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00076.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00076.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00076.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00077.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00077.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00077.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00077.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00077.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00077.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00078.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00078.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00078.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00078.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00078.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00078.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00079.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00079.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00079.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00079.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00079.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00079.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00080.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00080.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00080.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00080.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00080.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00080.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00081.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00081.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00081.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00081.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00081.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00081.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00082.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00082.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00082.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00082.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00082.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00082.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00083.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00083.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00083.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00083.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00083.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00083.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00084.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00084.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00084.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00084.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00084.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00084.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00085.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00085.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00085.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00085.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00085.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00085.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00086.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00086.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00086.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00086.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00086.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00086.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00087.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00087.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00087.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00087.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00087.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00087.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00088.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00088.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00088.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00088.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00088.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00088.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00089.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00089.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00089.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00089.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00089.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00089.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00090.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00090.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00090.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00090.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00090.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00090.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00091.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00091.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00091.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00091.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00091.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00091.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00092.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00092.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00092.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00092.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00092.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00092.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00093.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00093.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00093.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00093.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00093.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00093.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00094.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00094.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00094.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00094.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00094.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00094.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00095.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00095.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00095.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00095.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00095.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00095.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00096.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00096.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00096.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00096.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00096.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00096.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00097.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00097.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00097.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00097.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00097.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00097.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00098.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00098.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00098.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00098.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00098.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00098.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00099.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00099.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00099.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00099.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00099.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\country\country.00099.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00000.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00000.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00000.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00000.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00000.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00000.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00001.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00001.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00001.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00001.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00001.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00001.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00002.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00002.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00002.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00002.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00002.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00002.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00003.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00003.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00003.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00003.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00003.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00003.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00004.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00004.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00004.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00004.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00004.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00004.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00005.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00005.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00005.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00005.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00005.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00005.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00006.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00006.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00006.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00006.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00006.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00006.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00007.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00007.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00007.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00007.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00007.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00007.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00008.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00008.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00008.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00008.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00008.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00008.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00009.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00009.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00009.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00009.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00009.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00009.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00010.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00010.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00010.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00010.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00010.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00010.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00011.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00011.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00011.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00011.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00011.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00011.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00012.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00012.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00012.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00012.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00012.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00012.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00013.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00013.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00013.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00013.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00013.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00013.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00014.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00014.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00014.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00014.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00014.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00014.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00015.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00015.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00015.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00015.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00015.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00015.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00016.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00016.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00016.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00016.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00016.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00016.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00017.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00017.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00017.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00017.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00017.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00017.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00018.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00018.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00018.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00018.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00018.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00018.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00019.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00019.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00019.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00019.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00019.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00019.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00020.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00020.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00020.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00020.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00020.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00020.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00021.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00021.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00021.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00021.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00021.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00021.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00022.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00022.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00022.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00022.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00022.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00022.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00023.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00023.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00023.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00023.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00023.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00023.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00024.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00024.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00024.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00024.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00024.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00024.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00025.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00025.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00025.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00025.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00025.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00025.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00026.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00026.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00026.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00026.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00026.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00026.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00027.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00027.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00027.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00027.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00027.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00027.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00028.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00028.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00028.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00028.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00028.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00028.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00029.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00029.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00029.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00029.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00029.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00029.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00030.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00030.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00030.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00030.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00030.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00030.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00031.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00031.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00031.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00031.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00031.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00031.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00032.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00032.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00032.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00032.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00032.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00032.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00033.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00033.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00033.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00033.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00033.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00033.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00034.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00034.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00034.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00034.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00034.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00034.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00035.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00035.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00035.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00035.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00035.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00035.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00036.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00036.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00036.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00036.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00036.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00036.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00037.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00037.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00037.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00037.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00037.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00037.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00038.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00038.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00038.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00038.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00038.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00038.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00039.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00039.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00039.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00039.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00039.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00039.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00040.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00040.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00040.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00040.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00040.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00040.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00041.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00041.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00041.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00041.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00041.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00041.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00042.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00042.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00042.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00042.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00042.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00042.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00043.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00043.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00043.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00043.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00043.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00043.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00044.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00044.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00044.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00044.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00044.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00044.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00045.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00045.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00045.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00045.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00045.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00045.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00046.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00046.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00046.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00046.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00046.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00046.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00047.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00047.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00047.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00047.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00047.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00047.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00048.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00048.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00048.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00048.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00048.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00048.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00049.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00049.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00049.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00049.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00049.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00049.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00050.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00050.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00050.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00050.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00050.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00050.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00051.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00051.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00051.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00051.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00051.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00051.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00052.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00052.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00052.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00052.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00052.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00052.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00053.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00053.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00053.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00053.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00053.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00053.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00054.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00054.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00054.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00054.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00054.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00054.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00055.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00055.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00055.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00055.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00055.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00055.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00056.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00056.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00056.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00056.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00056.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00056.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00057.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00057.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00057.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00057.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00057.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00057.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00058.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00058.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00058.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00058.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00058.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00058.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00059.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00059.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00059.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00059.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00059.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00059.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00060.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00060.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00060.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00060.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00060.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00060.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00061.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00061.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00061.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00061.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00061.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00061.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00062.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00062.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00062.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00062.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00062.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00062.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00063.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00063.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00063.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00063.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00063.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00063.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00064.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00064.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00064.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00064.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00064.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00064.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00065.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00065.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00065.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00065.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00065.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00065.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00066.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00066.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00066.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00066.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00066.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00066.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00067.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00067.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00067.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00067.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00067.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00067.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00068.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00068.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00068.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00068.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00068.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00068.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00069.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00069.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00069.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00069.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00069.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00069.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00070.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00070.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00070.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00070.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00070.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00070.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00071.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00071.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00071.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00071.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00071.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00071.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00072.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00072.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00072.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00072.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00072.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00072.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00073.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00073.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00073.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00073.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00073.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00073.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00074.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00074.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00074.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00074.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00074.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00074.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00075.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00075.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00075.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00075.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00075.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00075.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00076.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00076.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00076.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00076.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00076.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00076.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00077.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00077.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00077.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00077.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00077.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00077.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00078.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00078.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00078.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00078.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00078.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00078.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00079.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00079.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00079.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00079.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00079.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00079.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00080.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00080.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00080.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00080.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00080.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00080.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00081.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00081.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00081.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00081.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00081.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00081.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00082.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00082.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00082.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00082.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00082.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00082.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00083.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00083.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00083.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00083.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00083.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00083.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00084.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00084.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00084.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00084.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00084.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00084.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00085.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00085.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00085.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00085.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00085.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00085.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00086.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00086.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00086.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00086.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00086.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00086.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00087.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00087.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00087.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00087.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00087.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00087.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00088.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00088.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00088.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00088.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00088.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00088.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00089.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00089.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00089.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00089.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00089.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00089.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00090.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00090.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00090.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00090.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00090.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00090.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00091.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00091.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00091.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00091.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00091.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00091.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00092.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00092.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00092.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00092.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00092.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00092.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00093.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00093.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00093.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00093.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00093.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00093.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00094.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00094.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00094.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00094.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00094.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00094.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00095.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00095.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00095.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00095.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00095.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00095.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00096.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00096.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00096.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00096.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00096.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00096.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00097.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00097.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00097.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00097.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00097.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00097.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00098.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00098.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00098.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00098.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00098.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00098.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00099.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00099.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00099.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00099.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00099.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\disco\disco.00099.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00000.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00000.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00000.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00000.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00000.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00000.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00001.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00001.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00001.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00001.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00001.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00001.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00002.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00002.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00002.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00002.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00002.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00002.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00003.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00003.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00003.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00003.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00003.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00003.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00004.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00004.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00004.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00004.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00004.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00004.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00005.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00005.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00005.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00005.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00005.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00005.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00006.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00006.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00006.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00006.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00006.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00006.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00007.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00007.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00007.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00007.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00007.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00007.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00008.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00008.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00008.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00008.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00008.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00008.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00009.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00009.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00009.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00009.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00009.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00009.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00010.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00010.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00010.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00010.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00010.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00010.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00011.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00011.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00011.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00011.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00011.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00011.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00012.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00012.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00012.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00012.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00012.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00012.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00013.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00013.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00013.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00013.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00013.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00013.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00014.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00014.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00014.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00014.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00014.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00014.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00015.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00015.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00015.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00015.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00015.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00015.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00016.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00016.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00016.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00016.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00016.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00016.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00017.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00017.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00017.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00017.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00017.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00017.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00018.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00018.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00018.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00018.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00018.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00018.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00019.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00019.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00019.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00019.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00019.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00019.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00020.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00020.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00020.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00020.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00020.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00020.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00021.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00021.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00021.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00021.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00021.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00021.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00022.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00022.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00022.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00022.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00022.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00022.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00023.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00023.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00023.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00023.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00023.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00023.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00024.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00024.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00024.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00024.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00024.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00024.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00025.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00025.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00025.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00025.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00025.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00025.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00026.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00026.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00026.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00026.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00026.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00026.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00027.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00027.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00027.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00027.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00027.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00027.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00028.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00028.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00028.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00028.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00028.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00028.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00029.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00029.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00029.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00029.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00029.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00029.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00030.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00030.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00030.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00030.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00030.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00030.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00031.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00031.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00031.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00031.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00031.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00031.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00032.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00032.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00032.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00032.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00032.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00033.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00033.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00033.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00033.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00033.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00033.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00034.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00034.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00034.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00034.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00034.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00034.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00035.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00035.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00035.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00035.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00035.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00035.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00036.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00036.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00036.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00036.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00036.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00036.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00037.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00037.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00037.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00037.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00037.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00037.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00038.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00038.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00038.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00038.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00038.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00038.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00039.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00039.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00039.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00039.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00039.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00039.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00040.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00040.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00040.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00040.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00040.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00040.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00041.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00041.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00041.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00041.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00041.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00041.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00042.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00042.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00042.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00042.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00042.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00042.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00043.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00043.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00043.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00043.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00043.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00043.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00044.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00044.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00044.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00044.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00044.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00044.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00045.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00045.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00045.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00045.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00045.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00045.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00046.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00046.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00046.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00046.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00046.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00046.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00047.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00047.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00047.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00047.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00047.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00047.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00048.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00048.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00048.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00048.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00048.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00048.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00049.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00049.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00049.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00049.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00049.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00049.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00050.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00050.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00050.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00050.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00050.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00050.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00051.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00051.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00051.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00051.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00051.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00051.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00052.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00052.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00052.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00052.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00052.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00052.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00053.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00053.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00053.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00053.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00053.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00053.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00054.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00054.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00054.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00054.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00054.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00054.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00055.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00055.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00055.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00055.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00055.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00055.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00056.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00056.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00056.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00056.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00056.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00056.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00057.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00057.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00057.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00057.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00057.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00057.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00058.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00058.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00058.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00058.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00058.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00058.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00059.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00059.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00059.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00059.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00059.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00059.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00060.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00060.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00060.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00060.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00060.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00060.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00061.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00061.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00061.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00061.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00061.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00061.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00062.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00062.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00062.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00062.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00062.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00062.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00063.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00063.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00063.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00063.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00063.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00063.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00064.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00064.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00064.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00064.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00064.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00064.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00065.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00065.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00065.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00065.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00065.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00065.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00066.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00066.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00066.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00066.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00066.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00066.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00067.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00067.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00067.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00067.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00067.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00067.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00068.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00068.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00068.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00068.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00068.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00068.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00069.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00069.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00069.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00069.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00069.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00069.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00070.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00070.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00070.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00070.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00070.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00070.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00071.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00071.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00071.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00071.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00071.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00071.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00072.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00072.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00072.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00072.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00072.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00072.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00073.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00073.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00073.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00073.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00073.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00073.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00074.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00074.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00074.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00074.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00074.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00074.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00075.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00075.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00075.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00075.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00075.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00075.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00076.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00076.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00076.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00076.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00076.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00076.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00077.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00077.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00077.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00077.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00077.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00077.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00078.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00078.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00078.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00078.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00078.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00078.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00079.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00079.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00079.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00079.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00079.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00079.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00080.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00080.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00080.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00080.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00080.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00080.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00081.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00081.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00081.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00081.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00081.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00081.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00082.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00082.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00082.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00082.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00082.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00082.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00083.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00083.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00083.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00083.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00083.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00083.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00084.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00084.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00084.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00084.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00084.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00084.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00085.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00085.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00085.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00085.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00085.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00085.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00086.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00086.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00086.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00086.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00086.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00086.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00087.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00087.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00087.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00087.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00087.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00087.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00088.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00088.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00088.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00088.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00088.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00088.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00089.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00089.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00089.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00089.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00089.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00089.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00090.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00090.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00090.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00090.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00090.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00090.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00091.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00091.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00091.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00091.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00091.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00091.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00092.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00092.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00092.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00092.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00092.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00092.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00093.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00093.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00093.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00093.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00093.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00093.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00094.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00094.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00094.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00094.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00094.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00094.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00095.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00095.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00095.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00095.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00095.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00095.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00096.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00096.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00096.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00096.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00096.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00096.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00097.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00097.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00097.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00097.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00097.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00097.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00098.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00098.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00098.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00098.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00098.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00098.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00099.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00099.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00099.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00099.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00099.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\hiphop\hiphop.00099.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00000.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00000.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00000.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00000.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00000.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00000.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00001.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00001.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00001.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00001.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00001.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00001.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00002.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00002.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00002.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00002.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00002.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00002.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00003.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00003.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00003.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00003.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00003.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00003.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00004.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00004.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00004.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00004.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00004.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00004.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00005.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00005.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00005.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00005.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00005.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00005.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00006.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00006.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00006.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00006.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00006.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00006.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00007.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00007.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00007.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00007.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00007.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00007.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00008.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00008.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00008.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00008.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00008.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00008.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00009.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00009.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00009.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00009.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00009.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00009.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00010.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00010.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00010.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00010.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00010.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00010.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00011.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00011.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00011.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00011.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00011.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00011.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00012.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00012.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00012.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00012.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00012.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00012.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00013.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00013.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00013.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00013.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00013.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00013.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00014.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00014.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00014.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00014.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00014.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00014.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00015.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00015.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00015.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00015.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00015.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00015.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00016.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00016.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00016.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00016.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00016.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00016.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00017.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00017.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00017.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00017.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00017.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00017.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00018.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00018.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00018.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00018.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00018.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00018.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00019.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00019.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00019.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00019.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00019.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00019.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00020.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00020.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00020.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00020.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00020.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00020.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00021.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00021.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00021.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00021.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00021.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00021.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00022.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00022.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00022.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00022.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00022.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00022.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00023.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00023.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00023.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00023.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00023.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00023.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00024.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00024.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00024.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00024.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00024.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00024.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00025.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00025.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00025.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00025.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00025.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00025.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00026.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00026.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00026.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00026.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00026.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00026.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00027.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00027.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00027.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00027.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00027.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00027.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00028.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00028.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00028.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00028.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00028.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00028.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00029.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00029.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00029.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00029.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00029.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00029.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00030.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00030.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00030.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00030.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00030.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00030.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00031.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00031.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00031.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00031.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00031.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00031.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00032.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00032.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00032.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00032.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00032.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00032.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00033.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00033.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00033.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00033.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00033.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00033.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00034.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00034.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00034.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00034.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00034.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00034.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00035.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00035.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00035.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00035.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00035.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00035.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00036.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00036.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00036.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00036.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00036.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00036.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00037.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00037.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00037.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00037.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00037.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00037.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00038.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00038.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00038.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00038.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00038.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00038.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00039.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00039.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00039.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00039.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00039.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00039.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00040.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00040.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00040.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00040.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00040.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00040.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00041.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00041.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00041.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00041.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00041.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00041.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00042.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00042.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00042.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00042.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00042.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00042.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00043.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00043.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00043.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00043.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00043.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00043.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00044.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00044.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00044.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00044.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00044.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00044.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00045.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00045.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00045.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00045.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00045.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00045.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00046.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00046.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00046.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00046.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00046.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00046.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00047.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00047.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00047.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00047.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00047.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00047.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00048.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00048.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00048.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00048.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00048.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00048.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00049.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00049.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00049.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00049.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00049.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00049.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00050.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00050.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00050.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00050.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00050.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00050.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00051.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00051.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00051.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00051.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00051.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00051.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00052.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00052.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00052.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00052.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00052.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00052.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00053.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00053.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00053.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00053.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00053.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00053.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00055.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00055.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00055.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00055.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00055.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00055.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00056.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00056.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00056.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00056.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00056.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00056.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00057.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00057.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00057.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00057.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00057.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00057.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00058.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00058.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00058.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00058.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00058.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00058.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00059.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00059.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00059.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00059.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00059.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00059.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00060.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00060.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00060.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00060.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00060.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00060.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00061.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00061.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00061.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00061.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00061.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00061.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00062.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00062.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00062.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00062.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00062.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00062.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00063.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00063.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00063.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00063.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00063.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00063.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00064.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00064.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00064.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00064.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00064.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00064.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00065.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00065.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00065.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00065.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00065.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00065.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00066.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00066.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00066.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00066.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00066.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00066.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00067.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00067.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00067.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00067.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00067.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00067.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00068.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00068.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00068.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00068.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00068.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00068.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00069.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00069.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00069.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00069.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00069.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00069.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00070.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00070.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00070.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00070.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00070.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00070.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00071.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00071.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00071.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00071.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00071.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00071.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00072.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00072.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00072.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00072.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00072.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00072.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00073.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00073.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00073.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00073.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00073.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00073.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00074.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00074.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00074.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00074.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00074.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00074.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00075.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00075.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00075.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00075.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00075.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00075.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00076.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00076.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00076.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00076.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00076.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00076.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00077.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00077.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00077.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00077.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00077.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00077.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00078.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00078.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00078.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00078.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00078.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00078.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00079.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00079.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00079.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00079.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00079.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00079.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00080.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00080.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00080.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00080.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00080.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00080.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00081.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00081.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00081.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00081.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00081.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00081.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00082.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00082.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00082.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00082.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00082.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00082.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00083.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00083.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00083.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00083.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00083.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00083.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00084.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00084.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00084.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00084.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00084.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00084.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00085.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00085.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00085.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00085.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00085.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00085.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00086.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00086.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00086.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00086.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00086.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00086.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00087.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00087.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00087.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00087.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00087.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00087.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00088.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00088.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00088.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00088.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00088.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00088.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00089.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00089.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00089.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00089.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00089.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00089.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00090.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00090.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00090.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00090.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00090.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00090.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00091.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00091.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00091.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00091.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00091.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00091.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00092.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00092.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00092.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00092.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00092.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00092.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00093.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00093.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00093.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00093.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00093.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00093.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00094.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00094.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00094.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00094.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00094.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00094.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00095.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00095.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00095.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00095.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00095.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00095.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00096.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00096.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00096.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00096.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00096.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00096.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00097.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00097.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00097.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00097.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00097.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00097.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00098.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00098.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00098.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00098.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00098.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00098.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00099.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00099.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00099.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00099.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00099.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\jazz\jazz.00099.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00000.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00000.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00000.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00000.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00000.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00000.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00001.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00001.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00001.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00001.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00001.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00001.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00002.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00002.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00002.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00002.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00002.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00002.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00003.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00003.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00003.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00003.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00003.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00003.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00004.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00004.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00004.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00004.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00004.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00004.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00005.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00005.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00005.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00005.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00005.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00005.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00006.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00006.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00006.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00006.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00006.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00006.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00007.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00007.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00007.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00007.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00007.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00007.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00008.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00008.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00008.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00008.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00008.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00008.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00009.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00009.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00009.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00009.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00009.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00009.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00010.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00010.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00010.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00010.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00010.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00010.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00011.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00011.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00011.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00011.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00011.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00011.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00012.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00012.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00012.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00012.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00012.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00012.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00013.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00013.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00013.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00013.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00013.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00013.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00014.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00014.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00014.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00014.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00014.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00014.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00015.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00015.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00015.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00015.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00015.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00015.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00016.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00016.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00016.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00016.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00016.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00016.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00017.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00017.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00017.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00017.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00017.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00017.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00018.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00018.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00018.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00018.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00018.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00018.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00019.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00019.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00019.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00019.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00019.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00019.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00020.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00020.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00020.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00020.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00020.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00020.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00021.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00021.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00021.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00021.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00021.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00021.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00022.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00022.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00022.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00022.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00022.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00022.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00023.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00023.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00023.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00023.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00023.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00023.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00024.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00024.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00024.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00024.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00024.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00024.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00025.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00025.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00025.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00025.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00025.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00025.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00026.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00026.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00026.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00026.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00026.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00026.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00027.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00027.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00027.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00027.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00027.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00027.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00028.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00028.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00028.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00028.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00028.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00028.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00029.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00029.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00029.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00029.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00029.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00029.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00030.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00030.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00030.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00030.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00030.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00030.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00031.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00031.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00031.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00031.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00031.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00031.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00032.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00032.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00032.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00032.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00032.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00032.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00033.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00033.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00033.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00033.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00033.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00033.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00034.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00034.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00034.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00034.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00034.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00034.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00035.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00035.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00035.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00035.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00035.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00035.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00036.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00036.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00036.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00036.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00036.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00036.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00037.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00037.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00037.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00037.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00037.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00037.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00038.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00038.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00038.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00038.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00038.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00038.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00039.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00039.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00039.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00039.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00039.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00039.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00040.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00040.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00040.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00040.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00040.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00040.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00041.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00041.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00041.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00041.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00041.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00041.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00042.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00042.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00042.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00042.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00042.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00042.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00043.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00043.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00043.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00043.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00043.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00043.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00044.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00044.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00044.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00044.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00044.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00044.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00045.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00045.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00045.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00045.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00045.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00045.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00046.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00046.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00046.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00046.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00046.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00046.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00047.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00047.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00047.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00047.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00047.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00047.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00048.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00048.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00048.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00048.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00048.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00048.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00049.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00049.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00049.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00049.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00049.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00049.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00050.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00050.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00050.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00050.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00050.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00050.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00051.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00051.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00051.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00051.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00051.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00051.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00052.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00052.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00052.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00052.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00052.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00052.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00053.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00053.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00053.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00053.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00053.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00053.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00054.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00054.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00054.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00054.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00054.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00054.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00055.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00055.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00055.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00055.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00055.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00055.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00056.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00056.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00056.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00056.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00056.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00056.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00057.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00057.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00057.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00057.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00057.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00057.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00058.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00058.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00058.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00058.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00058.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00058.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00059.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00059.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00059.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00059.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00059.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00059.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00060.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00060.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00060.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00060.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00060.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00060.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00061.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00061.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00061.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00061.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00061.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00061.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00062.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00062.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00062.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00062.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00062.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00062.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00063.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00063.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00063.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00063.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00063.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00063.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00064.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00064.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00064.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00064.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00064.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00064.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00065.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00065.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00065.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00065.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00065.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00065.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00066.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00066.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00066.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00066.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00066.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00066.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00067.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00067.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00067.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00067.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00067.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00067.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00068.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00068.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00068.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00068.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00068.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00068.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00069.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00069.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00069.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00069.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00069.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00069.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00070.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00070.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00070.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00070.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00070.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00070.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00071.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00071.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00071.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00071.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00071.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00071.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00072.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00072.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00072.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00072.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00072.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00072.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00073.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00073.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00073.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00073.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00073.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00073.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00074.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00074.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00074.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00074.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00074.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00074.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00075.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00075.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00075.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00075.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00075.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00075.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00076.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00076.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00076.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00076.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00076.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00076.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00077.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00077.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00077.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00077.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00077.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00077.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00078.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00078.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00078.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00078.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00078.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00078.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00079.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00079.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00079.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00079.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00079.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00079.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00080.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00080.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00080.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00080.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00080.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00080.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00081.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00081.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00081.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00081.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00081.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00081.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00082.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00082.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00082.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00082.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00082.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00082.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00083.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00083.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00083.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00083.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00083.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00083.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00084.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00084.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00084.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00084.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00084.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00084.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00085.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00085.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00085.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00085.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00085.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00085.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00086.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00086.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00086.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00086.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00086.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00086.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00087.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00087.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00087.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00087.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00087.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00087.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00088.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00088.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00088.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00088.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00088.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00088.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00089.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00089.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00089.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00089.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00089.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00089.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00090.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00090.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00090.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00090.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00090.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00090.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00091.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00091.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00091.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00091.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00091.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00091.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00092.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00092.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00092.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00092.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00092.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00092.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00093.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00093.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00093.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00093.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00093.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00093.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00094.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00094.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00094.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00094.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00094.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00094.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00095.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00095.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00095.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00095.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00095.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00095.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00096.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00096.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00096.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00096.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00096.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00096.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00097.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00097.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00097.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00097.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00097.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00097.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00098.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00098.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00098.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00098.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00098.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00098.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00099.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00099.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00099.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00099.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00099.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\metal\metal.00099.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00000.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00000.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00000.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00000.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00000.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00000.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00001.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00001.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00001.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00001.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00001.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00001.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00002.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00002.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00002.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00002.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00002.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00002.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00003.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00003.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00003.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00003.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00003.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00003.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00004.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00004.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00004.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00004.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00004.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00004.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00005.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00005.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00005.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00005.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00005.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00005.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00006.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00006.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00006.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00006.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00006.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00006.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00007.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00007.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00007.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00007.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00007.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00007.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00008.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00008.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00008.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00008.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00008.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00008.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00009.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00009.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00009.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00009.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00009.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00009.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00010.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00010.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00010.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00010.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00010.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00010.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00011.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00011.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00011.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00011.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00011.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00011.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00012.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00012.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00012.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00012.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00012.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00012.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00013.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00013.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00013.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00013.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00013.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00013.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00014.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00014.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00014.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00014.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00014.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00014.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00015.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00015.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00015.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00015.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00015.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00015.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00016.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00016.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00016.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00016.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00016.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00016.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00017.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00017.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00017.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00017.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00017.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00017.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00018.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00018.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00018.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00018.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00018.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00018.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00019.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00019.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00019.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00019.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00019.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00019.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00020.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00020.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00020.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00020.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00020.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00020.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00021.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00021.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00021.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00021.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00021.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00021.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00022.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00022.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00022.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00022.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00022.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00022.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00023.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00023.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00023.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00023.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00023.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00023.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00024.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00024.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00024.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00024.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00024.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00024.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00025.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00025.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00025.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00025.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00025.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00025.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00026.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00026.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00026.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00026.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00026.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00026.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00027.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00027.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00027.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00027.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00027.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00027.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00028.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00028.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00028.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00028.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00028.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00028.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00029.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00029.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00029.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00029.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00029.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00029.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00030.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00030.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00030.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00030.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00030.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00030.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00031.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00031.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00031.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00031.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00031.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00031.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00032.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00032.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00032.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00032.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00032.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00032.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00033.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00033.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00033.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00033.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00033.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00033.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00034.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00034.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00034.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00034.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00034.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00034.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00035.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00035.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00035.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00035.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00035.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00035.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00036.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00036.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00036.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00036.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00036.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00036.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00037.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00037.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00037.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00037.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00037.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00037.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00038.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00038.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00038.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00038.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00038.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00038.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00039.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00039.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00039.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00039.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00039.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00039.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00040.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00040.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00040.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00040.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00040.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00040.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00041.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00041.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00041.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00041.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00041.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00041.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00042.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00042.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00042.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00042.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00042.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00042.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00043.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00043.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00043.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00043.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00043.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00043.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00044.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00044.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00044.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00044.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00044.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00044.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00045.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00045.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00045.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00045.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00045.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00045.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00046.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00046.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00046.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00046.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00046.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00046.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00047.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00047.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00047.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00047.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00047.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00047.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00048.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00048.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00048.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00048.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00048.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00048.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00049.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00049.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00049.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00049.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00049.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00049.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00050.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00050.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00050.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00050.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00050.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00050.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00051.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00051.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00051.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00051.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00051.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00051.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00052.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00052.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00052.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00052.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00052.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00052.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00053.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00053.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00053.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00053.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00053.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00053.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00054.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00054.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00054.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00054.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00054.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00054.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00055.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00055.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00055.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00055.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00055.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00055.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00056.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00056.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00056.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00056.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00056.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00056.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00057.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00057.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00057.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00057.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00057.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00057.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00058.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00058.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00058.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00058.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00058.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00058.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00059.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00059.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00059.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00059.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00059.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00059.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00060.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00060.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00060.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00060.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00060.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00060.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00061.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00061.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00061.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00061.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00061.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00061.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00062.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00062.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00062.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00062.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00062.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00062.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00063.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00063.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00063.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00063.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00063.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00063.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00064.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00064.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00064.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00064.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00064.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00064.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00065.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00065.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00065.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00065.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00065.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00065.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00066.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00066.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00066.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00066.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00066.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00066.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00067.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00067.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00067.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00067.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00067.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00067.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00068.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00068.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00068.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00068.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00068.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00068.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00069.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00069.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00069.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00069.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00069.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00069.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00070.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00070.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00070.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00070.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00070.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00070.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00071.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00071.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00071.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00071.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00071.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00071.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00072.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00072.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00072.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00072.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00072.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00072.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00073.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00073.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00073.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00073.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00073.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00073.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00074.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00074.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00074.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00074.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00074.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00074.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00075.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00075.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00075.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00075.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00075.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00075.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00076.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00076.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00076.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00076.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00076.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00076.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00077.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00077.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00077.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00077.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00077.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00077.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00078.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00078.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00078.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00078.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00078.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00078.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00079.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00079.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00079.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00079.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00079.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00079.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00080.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00080.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00080.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00080.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00080.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00080.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00081.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00081.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00081.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00081.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00081.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00081.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00082.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00082.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00082.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00082.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00082.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00082.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00083.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00083.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00083.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00083.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00083.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00083.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00084.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00084.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00084.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00084.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00084.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00084.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00085.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00085.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00085.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00085.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00085.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00085.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00086.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00086.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00086.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00086.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00086.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00086.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00087.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00087.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00087.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00087.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00087.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00087.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00088.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00088.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00088.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00088.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00088.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00088.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00089.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00089.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00089.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00089.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00089.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00089.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00090.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00090.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00090.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00090.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00090.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00090.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00091.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00091.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00091.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00091.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00091.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00091.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00092.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00092.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00092.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00092.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00092.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00092.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00093.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00093.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00093.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00093.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00093.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00093.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00094.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00094.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00094.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00094.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00094.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00094.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00095.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00095.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00095.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00095.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00095.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00095.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00096.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00096.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00096.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00096.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00096.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00096.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00097.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00097.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00097.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00097.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00097.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00097.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00098.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00098.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00098.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00098.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00098.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00098.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00099.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00099.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00099.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00099.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00099.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\pop\pop.00099.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00000.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00000.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00000.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00000.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00000.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00000.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00001.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00001.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00001.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00001.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00001.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00001.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00002.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00002.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00002.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00002.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00002.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00002.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00003.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00003.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00003.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00003.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00003.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00003.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00004.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00004.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00004.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00004.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00004.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00004.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00005.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00005.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00005.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00005.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00005.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00005.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00006.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00006.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00006.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00006.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00006.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00006.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00007.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00007.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00007.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00007.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00007.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00007.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00008.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00008.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00008.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00008.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00008.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00008.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00009.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00009.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00009.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00009.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00009.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00009.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00010.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00010.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00010.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00010.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00010.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00010.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00011.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00011.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00011.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00011.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00011.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00011.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00012.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00012.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00012.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00012.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00012.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00012.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00013.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00013.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00013.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00013.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00013.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00013.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00014.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00014.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00014.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00014.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00014.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00014.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00015.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00015.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00015.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00015.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00015.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00015.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00016.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00016.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00016.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00016.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00016.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00016.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00017.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00017.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00017.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00017.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00017.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00017.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00018.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00018.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00018.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00018.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00018.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00018.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00019.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00019.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00019.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00019.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00019.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00019.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00020.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00020.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00020.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00020.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00020.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00020.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00021.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00021.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00021.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00021.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00021.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00021.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00022.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00022.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00022.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00022.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00022.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00022.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00023.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00023.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00023.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00023.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00023.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00023.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00024.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00024.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00024.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00024.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00024.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00024.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00025.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00025.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00025.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00025.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00025.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00025.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00026.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00026.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00026.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00026.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00026.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00026.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00027.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00027.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00027.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00027.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00027.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00027.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00028.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00028.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00028.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00028.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00028.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00028.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00029.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00029.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00029.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00029.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00029.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00029.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00030.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00030.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00030.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00030.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00030.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00030.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00031.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00031.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00031.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00031.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00031.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00031.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00032.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00032.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00032.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00032.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00032.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00032.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00033.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00033.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00033.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00033.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00033.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00033.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00034.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00034.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00034.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00034.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00034.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00034.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00035.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00035.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00035.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00035.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00035.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00035.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00036.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00036.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00036.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00036.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00036.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00036.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00037.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00037.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00037.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00037.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00037.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00037.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00038.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00038.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00038.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00038.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00038.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00038.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00039.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00039.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00039.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00039.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00039.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00039.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00040.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00040.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00040.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00040.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00040.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00040.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00041.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00041.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00041.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00041.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00041.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00041.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00042.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00042.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00042.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00042.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00042.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00042.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00043.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00043.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00043.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00043.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00043.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00043.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00044.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00044.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00044.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00044.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00044.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00044.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00045.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00045.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00045.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00045.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00045.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00045.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00046.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00046.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00046.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00046.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00046.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00046.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00047.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00047.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00047.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00047.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00047.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00047.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00048.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00048.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00048.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00048.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00048.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00048.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00049.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00049.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00049.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00049.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00049.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00049.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00050.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00050.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00050.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00050.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00050.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00050.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00051.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00051.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00051.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00051.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00051.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00051.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00052.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00052.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00052.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00052.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00052.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00052.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00053.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00053.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00053.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00053.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00053.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00053.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00054.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00054.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00054.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00054.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00054.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00054.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00055.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00055.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00055.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00055.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00055.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00055.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00056.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00056.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00056.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00056.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00056.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00056.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00057.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00057.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00057.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00057.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00057.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00057.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00058.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00058.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00058.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00058.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00058.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00058.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00059.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00059.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00059.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00059.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00059.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00059.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00060.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00060.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00060.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00060.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00060.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00060.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00061.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00061.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00061.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00061.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00061.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00061.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00062.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00062.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00062.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00062.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00062.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00062.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00063.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00063.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00063.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00063.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00063.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00063.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00064.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00064.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00064.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00064.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00064.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00064.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00065.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00065.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00065.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00065.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00065.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00065.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00066.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00066.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00066.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00066.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00066.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00066.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00067.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00067.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00067.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00067.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00067.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00067.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00068.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00068.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00068.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00068.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00068.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00068.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00069.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00069.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00069.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00069.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00069.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00069.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00070.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00070.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00070.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00070.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00070.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00070.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00071.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00071.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00071.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00071.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00071.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00071.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00072.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00072.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00072.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00072.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00072.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00072.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00073.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00073.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00073.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00073.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00073.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00073.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00074.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00074.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00074.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00074.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00074.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00074.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00075.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00075.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00075.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00075.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00075.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00075.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00076.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00076.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00076.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00076.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00076.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00076.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00077.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00077.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00077.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00077.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00077.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00077.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00078.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00078.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00078.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00078.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00078.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00078.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00079.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00079.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00079.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00079.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00079.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00079.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00080.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00080.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00080.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00080.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00080.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00080.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00081.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00081.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00081.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00081.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00081.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00081.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00082.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00082.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00082.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00082.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00082.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00082.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00083.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00083.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00083.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00083.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00083.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00083.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00084.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00084.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00084.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00084.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00084.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00084.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00085.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00085.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00085.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00085.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00085.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00085.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00086.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00086.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00086.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00086.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00086.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00086.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00087.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00087.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00087.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00087.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00087.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00087.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00088.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00088.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00088.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00088.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00088.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00088.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00089.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00089.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00089.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00089.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00089.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00089.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00090.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00090.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00090.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00090.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00090.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00090.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00091.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00091.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00091.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00091.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00091.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00091.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00092.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00092.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00092.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00092.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00092.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00092.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00093.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00093.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00093.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00093.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00093.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00093.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00094.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00094.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00094.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00094.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00094.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00094.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00095.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00095.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00095.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00095.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00095.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00095.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00096.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00096.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00096.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00096.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00096.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00096.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00097.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00097.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00097.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00097.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00097.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00097.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00098.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00098.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00098.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00098.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00098.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00098.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00099.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00099.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00099.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00099.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00099.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\reggae\reggae.00099.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00000.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00000.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00000.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00000.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00000.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00000.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00001.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00001.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00001.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00001.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00001.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00001.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00002.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00002.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00002.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00002.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00002.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00002.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00003.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00003.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00003.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00003.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00003.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00003.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00004.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00004.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00004.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00004.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00004.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00004.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00005.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00005.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00005.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00005.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00005.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00005.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00006.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00006.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00006.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00006.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00006.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00006.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00007.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00007.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00007.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00007.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00007.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00007.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00008.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00008.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00008.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00008.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00008.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00008.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00009.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00009.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00009.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00009.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00009.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00009.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00010.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00010.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00010.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00010.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00010.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00010.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00011.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00011.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00011.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00011.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00011.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00011.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00012.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00012.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00012.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00012.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00012.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00012.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00013.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00013.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00013.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00013.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00013.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00013.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00014.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00014.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00014.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00014.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00014.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00014.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00015.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00015.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00015.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00015.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00015.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00015.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00016.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00016.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00016.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00016.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00016.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00016.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00017.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00017.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00017.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00017.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00017.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00017.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00018.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00018.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00018.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00018.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00018.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00018.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00019.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00019.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00019.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00019.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00019.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00019.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00020.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00020.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00020.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00020.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00020.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00020.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00021.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00021.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00021.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00021.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00021.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00021.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00022.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00022.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00022.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00022.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00022.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00022.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00023.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00023.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00023.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00023.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00023.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00023.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00024.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00024.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00024.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00024.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00024.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00024.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00025.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00025.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00025.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00025.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00025.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00025.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00026.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00026.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00026.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00026.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00026.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00026.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00027.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00027.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00027.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00027.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00027.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00027.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00028.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00028.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00028.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00028.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00028.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00028.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00029.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00029.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00029.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00029.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00029.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00029.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00030.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00030.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00030.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00030.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00030.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00030.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00031.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00031.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00031.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00031.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00031.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00031.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00032.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00032.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00032.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00032.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00032.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00032.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00033.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00033.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00033.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00033.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00033.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00033.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00034.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00034.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00034.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00034.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00034.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00034.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00035.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00035.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00035.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00035.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00035.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00035.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00036.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00036.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00036.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00036.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00036.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00036.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00037.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00037.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00037.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00037.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00037.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00037.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00038.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00038.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00038.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00038.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00038.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00038.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00039.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00039.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00039.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00039.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00039.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00039.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00040.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00040.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00040.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00040.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00040.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00040.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00041.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00041.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00041.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00041.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00041.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00041.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00042.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00042.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00042.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00042.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00042.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00042.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00043.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00043.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00043.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00043.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00043.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00043.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00044.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00044.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00044.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00044.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00044.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00044.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00045.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00045.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00045.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00045.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00045.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00045.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00046.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00046.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00046.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00046.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00046.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00046.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00047.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00047.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00047.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00047.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00047.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00047.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00048.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00048.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00048.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00048.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00048.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00048.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00049.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00049.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00049.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00049.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00049.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00049.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00050.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00050.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00050.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00050.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00050.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00050.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00051.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00051.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00051.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00051.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00051.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00051.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00052.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00052.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00052.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00052.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00052.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00052.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00053.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00053.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00053.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00053.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00053.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00053.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00054.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00054.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00054.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00054.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00054.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00054.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00055.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00055.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00055.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00055.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00055.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00055.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00056.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00056.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00056.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00056.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00056.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00056.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00057.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00057.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00057.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00057.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00057.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00057.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00058.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00058.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00058.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00058.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00058.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00058.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00059.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00059.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00059.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00059.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00059.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00059.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00060.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00060.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00060.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00060.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00060.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00060.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00061.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00061.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00061.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00061.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00061.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00061.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00062.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00062.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00062.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00062.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00062.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00062.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00063.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00063.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00063.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00063.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00063.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00063.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00064.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00064.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00064.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00064.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00064.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00064.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00065.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00065.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00065.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00065.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00065.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00065.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00066.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00066.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00066.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00066.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00066.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00066.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00067.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00067.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00067.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00067.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00067.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00067.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00068.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00068.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00068.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00068.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00068.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00068.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00069.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00069.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00069.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00069.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00069.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00069.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00070.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00070.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00070.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00070.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00070.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00070.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00071.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00071.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00071.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00071.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00071.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00071.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00072.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00072.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00072.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00072.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00072.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00072.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00073.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00073.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00073.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00073.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00073.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00073.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00074.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00074.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00074.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00074.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00074.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00074.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00075.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00075.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00075.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00075.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00075.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00075.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00076.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00076.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00076.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00076.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00076.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00076.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00077.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00077.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00077.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00077.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00077.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00077.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00078.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00078.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00078.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00078.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00078.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00078.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00079.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00079.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00079.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00079.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00079.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00079.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00080.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00080.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00080.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00080.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00080.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00080.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00081.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00081.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00081.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00081.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00081.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00081.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00082.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00082.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00082.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00082.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00082.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00082.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00083.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00083.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00083.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00083.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00083.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00083.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00084.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00084.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00084.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00084.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00084.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00084.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00085.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00085.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00085.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00085.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00085.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00085.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00086.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00086.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00086.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00086.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00086.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00086.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00087.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00087.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00087.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00087.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00087.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00087.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00088.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00088.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00088.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00088.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00088.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00088.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00089.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00089.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00089.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00089.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00089.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00089.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00090.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00090.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00090.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00090.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00090.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00090.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00091.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00091.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00091.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00091.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00091.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00091.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00092.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00092.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00092.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00092.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00092.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00092.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00093.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00093.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00093.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00093.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00093.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00093.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00094.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00094.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00094.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00094.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00094.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00094.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00095.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00095.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00095.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00095.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00095.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00095.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00096.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00096.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00096.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00096.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00096.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00096.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00097.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00097.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00097.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00097.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00097.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00097.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00098.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00098.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00098.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00098.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00098.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00098.wav, segment:6 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00099.wav, segment:1 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00099.wav, segment:2 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00099.wav, segment:3 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00099.wav, segment:4 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00099.wav, segment:5 F:\Study_content\UCD\zSemester2\jupyter_notebook\COMP47650.Deep_learning\Individual_Project\Comp47650_Yinjie_Liu_20211091\Data\genres_original\rock\rock.00099.wav, segment:6 Model: "sequential" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= conv2d (Conv2D) (None, 214, 11, 32) 320 _________________________________________________________________ max_pooling2d (MaxPooling2D) (None, 107, 6, 32) 0 _________________________________________________________________ batch_normalization (BatchNo (None, 107, 6, 32) 128 _________________________________________________________________ conv2d_1 (Conv2D) (None, 105, 4, 32) 9248 _________________________________________________________________ max_pooling2d_1 (MaxPooling2 (None, 53, 2, 32) 0 _________________________________________________________________ batch_normalization_1 (Batch (None, 53, 2, 32) 128 _________________________________________________________________ conv2d_2 (Conv2D) (None, 52, 1, 32) 4128 _________________________________________________________________ max_pooling2d_2 (MaxPooling2 (None, 26, 1, 32) 0 _________________________________________________________________ batch_normalization_2 (Batch (None, 26, 1, 32) 128 _________________________________________________________________ flatten (Flatten) (None, 832) 0 _________________________________________________________________ dense (Dense) (None, 64) 53312 _________________________________________________________________ dropout (Dropout) (None, 64) 0 _________________________________________________________________ dense_1 (Dense) (None, 10) 650 ================================================================= Total params: 68,042 Trainable params: 67,850 Non-trainable params: 192 _________________________________________________________________ Train on 3595 samples, validate on 899 samples Epoch 1/30 32/3595 [..............................] - ETA: 3:02 - loss: 3.0191 - accuracy: 0.1562 160/3595 [>.............................] - ETA: 36s - loss: 2.9068 - accuracy: 0.1312 256/3595 [=>............................] - ETA: 23s - loss: 2.8786 - accuracy: 0.1406 416/3595 [==>...........................] - ETA: 13s - loss: 2.8795 - accuracy: 0.1418 544/3595 [===>..........................] - ETA: 10s - loss: 2.8217 - accuracy: 0.1415 672/3595 [====>.........................] - ETA: 8s - loss: 2.8021 - accuracy: 0.1354 800/3595 [=====>........................] - ETA: 7s - loss: 2.7915 - accuracy: 0.1363 960/3595 [=======>......................] - ETA: 5s - loss: 2.7718 - accuracy: 0.1375 1088/3595 [========>.....................] - ETA: 4s - loss: 2.7631 - accuracy: 0.1406 1216/3595 [=========>....................] - ETA: 4s - loss: 2.7317 - accuracy: 0.1414 1344/3595 [==========>...................] - ETA: 3s - loss: 2.7065 - accuracy: 0.1466 1472/3595 [===========>..................] - ETA: 3s - loss: 2.6714 - accuracy: 0.1522 1600/3595 [============>.................] - ETA: 2s - loss: 2.6363 - accuracy: 0.1600 1728/3595 [=============>................] - ETA: 2s - loss: 2.6049 - accuracy: 0.1649 1888/3595 [==============>...............] - ETA: 2s - loss: 2.5868 - accuracy: 0.1711 2016/3595 [===============>..............] - ETA: 2s - loss: 2.5728 - accuracy: 0.1731 2144/3595 [================>.............] - ETA: 1s - loss: 2.5628 - accuracy: 0.1754 2272/3595 [=================>............] - ETA: 1s - loss: 2.5462 - accuracy: 0.1805 2400/3595 [===================>..........] - ETA: 1s - loss: 2.5274 - accuracy: 0.1842 2528/3595 [====================>.........] - ETA: 1s - loss: 2.5122 - accuracy: 0.1879 2656/3595 [=====================>........] - ETA: 1s - loss: 2.4956 - accuracy: 0.1916 2816/3595 [======================>.......] - ETA: 0s - loss: 2.4753 - accuracy: 0.1978 2944/3595 [=======================>......] - ETA: 0s - loss: 2.4648 - accuracy: 0.1994 3072/3595 [========================>.....] - ETA: 0s - loss: 2.4429 - accuracy: 0.2028 3200/3595 [=========================>....] - ETA: 0s - loss: 2.4286 - accuracy: 0.2050 3328/3595 [==========================>...] - ETA: 0s - loss: 2.4179 - accuracy: 0.2091 3456/3595 [===========================>..] - ETA: 0s - loss: 2.4110 - accuracy: 0.2138 3584/3595 [============================>.] - ETA: 0s - loss: 2.3956 - accuracy: 0.2182 3595/3595 [==============================] - 4s 1ms/sample - loss: 2.3952 - accuracy: 0.2186 - val_loss: 2.0284 - val_accuracy: 0.2558 Epoch 2/30 32/3595 [..............................] - ETA: 1s - loss: 1.9988 - accuracy: 0.3750 160/3595 [>.............................] - ETA: 1s - loss: 2.0622 - accuracy: 0.3187 320/3595 [=>............................] - ETA: 1s - loss: 2.0231 - accuracy: 0.3094 448/3595 [==>...........................] - ETA: 1s - loss: 2.0032 - accuracy: 0.3281 608/3595 [====>.........................] - ETA: 1s - loss: 1.9838 - accuracy: 0.3322 704/3595 [====>.........................] - ETA: 1s - loss: 1.9527 - accuracy: 0.3438 864/3595 [======>.......................] - ETA: 1s - loss: 1.9626 - accuracy: 0.3461 992/3595 [=======>......................] - ETA: 1s - loss: 1.9652 - accuracy: 0.3478 1120/3595 [========>.....................] - ETA: 1s - loss: 1.9564 - accuracy: 0.3429 1248/3595 [=========>....................] - ETA: 1s - loss: 1.9639 - accuracy: 0.3357 1344/3595 [==========>...................] - ETA: 1s - loss: 1.9568 - accuracy: 0.3356 1472/3595 [===========>..................] - ETA: 1s - loss: 1.9305 - accuracy: 0.3424 1600/3595 [============>.................] - ETA: 0s - loss: 1.9209 - accuracy: 0.3419 1728/3595 [=============>................] - ETA: 0s - loss: 1.9285 - accuracy: 0.3409 1856/3595 [==============>...............] - ETA: 0s - loss: 1.9270 - accuracy: 0.3432 1984/3595 [===============>..............] - ETA: 0s - loss: 1.9213 - accuracy: 0.3417 2112/3595 [================>.............] - ETA: 0s - loss: 1.9174 - accuracy: 0.3438 2272/3595 [=================>............] - ETA: 0s - loss: 1.9106 - accuracy: 0.3451 2400/3595 [===================>..........] - ETA: 0s - loss: 1.9124 - accuracy: 0.3450 2528/3595 [====================>.........] - ETA: 0s - loss: 1.9165 - accuracy: 0.3438 2656/3595 [=====================>........] - ETA: 0s - loss: 1.9145 - accuracy: 0.3445 2816/3595 [======================>.......] - ETA: 0s - loss: 1.9109 - accuracy: 0.3466 2944/3595 [=======================>......] - ETA: 0s - loss: 1.9051 - accuracy: 0.3475 3072/3595 [========================>.....] - ETA: 0s - loss: 1.8991 - accuracy: 0.3493 3200/3595 [=========================>....] - ETA: 0s - loss: 1.8972 - accuracy: 0.3475 3328/3595 [==========================>...] - ETA: 0s - loss: 1.8940 - accuracy: 0.3489 3488/3595 [============================>.] - ETA: 0s - loss: 1.8865 - accuracy: 0.3501 3595/3595 [==============================] - 2s 509us/sample - loss: 1.8911 - accuracy: 0.3491 - val_loss: 1.6867 - val_accuracy: 0.3971 Epoch 3/30 32/3595 [..............................] - ETA: 1s - loss: 1.8052 - accuracy: 0.4688 192/3595 [>.............................] - ETA: 1s - loss: 1.6651 - accuracy: 0.4323 288/3595 [=>............................] - ETA: 1s - loss: 1.6154 - accuracy: 0.4479 416/3595 [==>...........................] - ETA: 1s - loss: 1.6157 - accuracy: 0.4471 544/3595 [===>..........................] - ETA: 1s - loss: 1.6668 - accuracy: 0.4283 672/3595 [====>.........................] - ETA: 1s - loss: 1.6773 - accuracy: 0.4256 800/3595 [=====>........................] - ETA: 1s - loss: 1.6884 - accuracy: 0.4263 928/3595 [======>.......................] - ETA: 1s - loss: 1.7011 - accuracy: 0.4203 1056/3595 [=======>......................] - ETA: 1s - loss: 1.7104 - accuracy: 0.4167 1184/3595 [========>.....................] - ETA: 1s - loss: 1.7095 - accuracy: 0.4164 1312/3595 [=========>....................] - ETA: 1s - loss: 1.7134 - accuracy: 0.4085 1472/3595 [===========>..................] - ETA: 1s - loss: 1.7058 - accuracy: 0.4130 1600/3595 [============>.................] - ETA: 0s - loss: 1.7082 - accuracy: 0.4094 1728/3595 [=============>................] - ETA: 0s - loss: 1.7199 - accuracy: 0.4057 1856/3595 [==============>...............] - ETA: 0s - loss: 1.7167 - accuracy: 0.4073 2016/3595 [===============>..............] - ETA: 0s - loss: 1.7223 - accuracy: 0.4033 2144/3595 [================>.............] - ETA: 0s - loss: 1.7235 - accuracy: 0.4030 2272/3595 [=================>............] - ETA: 0s - loss: 1.7173 - accuracy: 0.4032 2400/3595 [===================>..........] - ETA: 0s - loss: 1.7236 - accuracy: 0.3979 2560/3595 [====================>.........] - ETA: 0s - loss: 1.7134 - accuracy: 0.4020 2720/3595 [=====================>........] - ETA: 0s - loss: 1.7123 - accuracy: 0.4044 2848/3595 [======================>.......] - ETA: 0s - loss: 1.7040 - accuracy: 0.4073 2976/3595 [=======================>......] - ETA: 0s - loss: 1.7047 - accuracy: 0.4076 3104/3595 [========================>.....] - ETA: 0s - loss: 1.7016 - accuracy: 0.4075 3232/3595 [=========================>....] - ETA: 0s - loss: 1.7059 - accuracy: 0.4084 3360/3595 [===========================>..] - ETA: 0s - loss: 1.6991 - accuracy: 0.4113 3520/3595 [============================>.] - ETA: 0s - loss: 1.6959 - accuracy: 0.4114 3595/3595 [==============================] - 2s 504us/sample - loss: 1.6975 - accuracy: 0.4120 - val_loss: 1.4911 - val_accuracy: 0.4650 Epoch 4/30 32/3595 [..............................] - ETA: 1s - loss: 1.4523 - accuracy: 0.5625 160/3595 [>.............................] - ETA: 1s - loss: 1.7470 - accuracy: 0.4375 288/3595 [=>............................] - ETA: 1s - loss: 1.7964 - accuracy: 0.4132 448/3595 [==>...........................] - ETA: 1s - loss: 1.6979 - accuracy: 0.4308 576/3595 [===>..........................] - ETA: 1s - loss: 1.6518 - accuracy: 0.4444 704/3595 [====>.........................] - ETA: 1s - loss: 1.6370 - accuracy: 0.4489 832/3595 [=====>........................] - ETA: 1s - loss: 1.6458 - accuracy: 0.4411 960/3595 [=======>......................] - ETA: 1s - loss: 1.6223 - accuracy: 0.4417 1088/3595 [========>.....................] - ETA: 1s - loss: 1.6160 - accuracy: 0.4421 1216/3595 [=========>....................] - ETA: 1s - loss: 1.6032 - accuracy: 0.4449 1344/3595 [==========>...................] - ETA: 1s - loss: 1.6174 - accuracy: 0.4382 1472/3595 [===========>..................] - ETA: 1s - loss: 1.6122 - accuracy: 0.4389 1632/3595 [============>.................] - ETA: 0s - loss: 1.6090 - accuracy: 0.4418 1760/3595 [=============>................] - ETA: 0s - loss: 1.6085 - accuracy: 0.4409 1888/3595 [==============>...............] - ETA: 0s - loss: 1.5925 - accuracy: 0.4449 2016/3595 [===============>..............] - ETA: 0s - loss: 1.5804 - accuracy: 0.4474 2144/3595 [================>.............] - ETA: 0s - loss: 1.5746 - accuracy: 0.4482 2272/3595 [=================>............] - ETA: 0s - loss: 1.5731 - accuracy: 0.4472 2400/3595 [===================>..........] - ETA: 0s - loss: 1.5648 - accuracy: 0.4500 2528/3595 [====================>.........] - ETA: 0s - loss: 1.5572 - accuracy: 0.4486 2656/3595 [=====================>........] - ETA: 0s - loss: 1.5641 - accuracy: 0.4447 2784/3595 [======================>.......] - ETA: 0s - loss: 1.5607 - accuracy: 0.4440 2912/3595 [=======================>......] - ETA: 0s - loss: 1.5630 - accuracy: 0.4437 3040/3595 [========================>.....] - ETA: 0s - loss: 1.5603 - accuracy: 0.4447 3168/3595 [=========================>....] - ETA: 0s - loss: 1.5530 - accuracy: 0.4467 3328/3595 [==========================>...] - ETA: 0s - loss: 1.5555 - accuracy: 0.4441 3456/3595 [===========================>..] - ETA: 0s - loss: 1.5618 - accuracy: 0.4433 3584/3595 [============================>.] - ETA: 0s - loss: 1.5605 - accuracy: 0.4428 3595/3595 [==============================] - 2s 509us/sample - loss: 1.5589 - accuracy: 0.4437 - val_loss: 1.3729 - val_accuracy: 0.5050 Epoch 5/30 32/3595 [..............................] - ETA: 1s - loss: 1.5616 - accuracy: 0.4375 160/3595 [>.............................] - ETA: 1s - loss: 1.4384 - accuracy: 0.4938 288/3595 [=>............................] - ETA: 1s - loss: 1.4709 - accuracy: 0.4826 448/3595 [==>...........................] - ETA: 1s - loss: 1.4410 - accuracy: 0.4911 576/3595 [===>..........................] - ETA: 1s - loss: 1.4328 - accuracy: 0.4965 704/3595 [====>.........................] - ETA: 1s - loss: 1.4520 - accuracy: 0.4844 832/3595 [=====>........................] - ETA: 1s - loss: 1.4587 - accuracy: 0.4844 928/3595 [======>.......................] - ETA: 1s - loss: 1.4652 - accuracy: 0.4795 1056/3595 [=======>......................] - ETA: 1s - loss: 1.4407 - accuracy: 0.4896 1184/3595 [========>.....................] - ETA: 1s - loss: 1.4304 - accuracy: 0.4899 1312/3595 [=========>....................] - ETA: 1s - loss: 1.4338 - accuracy: 0.4901 1440/3595 [===========>..................] - ETA: 1s - loss: 1.4230 - accuracy: 0.4896 1568/3595 [============>.................] - ETA: 1s - loss: 1.4175 - accuracy: 0.4923 1696/3595 [=============>................] - ETA: 0s - loss: 1.4133 - accuracy: 0.4935 1824/3595 [==============>...............] - ETA: 0s - loss: 1.4145 - accuracy: 0.4907 1984/3595 [===============>..............] - ETA: 0s - loss: 1.4148 - accuracy: 0.4899 2112/3595 [================>.............] - ETA: 0s - loss: 1.4217 - accuracy: 0.4886 2240/3595 [=================>............] - ETA: 0s - loss: 1.4221 - accuracy: 0.4871 2368/3595 [==================>...........] - ETA: 0s - loss: 1.4159 - accuracy: 0.4882 2464/3595 [===================>..........] - ETA: 0s - loss: 1.4176 - accuracy: 0.4870 2624/3595 [====================>.........] - ETA: 0s - loss: 1.4308 - accuracy: 0.4802 2752/3595 [=====================>........] - ETA: 0s - loss: 1.4283 - accuracy: 0.4804 2880/3595 [=======================>......] - ETA: 0s - loss: 1.4237 - accuracy: 0.4823 3008/3595 [========================>.....] - ETA: 0s - loss: 1.4202 - accuracy: 0.4837 3136/3595 [=========================>....] - ETA: 0s - loss: 1.4193 - accuracy: 0.4857 3296/3595 [==========================>...] - ETA: 0s - loss: 1.4115 - accuracy: 0.4885 3424/3595 [===========================>..] - ETA: 0s - loss: 1.4143 - accuracy: 0.4895 3552/3595 [============================>.] - ETA: 0s - loss: 1.4163 - accuracy: 0.4887 3595/3595 [==============================] - 2s 513us/sample - loss: 1.4155 - accuracy: 0.4887 - val_loss: 1.3245 - val_accuracy: 0.5217 Epoch 6/30 32/3595 [..............................] - ETA: 1s - loss: 1.3167 - accuracy: 0.5312 160/3595 [>.............................] - ETA: 1s - loss: 1.3073 - accuracy: 0.4875 288/3595 [=>............................] - ETA: 1s - loss: 1.3979 - accuracy: 0.4722 384/3595 [==>...........................] - ETA: 1s - loss: 1.3604 - accuracy: 0.4922 512/3595 [===>..........................] - ETA: 1s - loss: 1.3569 - accuracy: 0.5039 672/3595 [====>.........................] - ETA: 1s - loss: 1.3252 - accuracy: 0.5134 800/3595 [=====>........................] - ETA: 1s - loss: 1.3410 - accuracy: 0.5138 928/3595 [======>.......................] - ETA: 1s - loss: 1.3287 - accuracy: 0.5172 1056/3595 [=======>......................] - ETA: 1s - loss: 1.3282 - accuracy: 0.5152 1216/3595 [=========>....................] - ETA: 1s - loss: 1.3255 - accuracy: 0.5164 1344/3595 [==========>...................] - ETA: 1s - loss: 1.3339 - accuracy: 0.5193 1472/3595 [===========>..................] - ETA: 1s - loss: 1.3393 - accuracy: 0.5183 1600/3595 [============>.................] - ETA: 0s - loss: 1.3364 - accuracy: 0.5206 1728/3595 [=============>................] - ETA: 0s - loss: 1.3282 - accuracy: 0.5226 1856/3595 [==============>...............] - ETA: 0s - loss: 1.3235 - accuracy: 0.5242 1984/3595 [===============>..............] - ETA: 0s - loss: 1.3293 - accuracy: 0.5217 2144/3595 [================>.............] - ETA: 0s - loss: 1.3143 - accuracy: 0.5308 2272/3595 [=================>............] - ETA: 0s - loss: 1.3125 - accuracy: 0.5317 2400/3595 [===================>..........] - ETA: 0s - loss: 1.3201 - accuracy: 0.5263 2528/3595 [====================>.........] - ETA: 0s - loss: 1.3225 - accuracy: 0.5257 2656/3595 [=====================>........] - ETA: 0s - loss: 1.3203 - accuracy: 0.5267 2816/3595 [======================>.......] - ETA: 0s - loss: 1.3223 - accuracy: 0.5263 2944/3595 [=======================>......] - ETA: 0s - loss: 1.3202 - accuracy: 0.5275 3072/3595 [========================>.....] - ETA: 0s - loss: 1.3171 - accuracy: 0.5270 3200/3595 [=========================>....] - ETA: 0s - loss: 1.3281 - accuracy: 0.5241 3328/3595 [==========================>...] - ETA: 0s - loss: 1.3293 - accuracy: 0.5225 3488/3595 [============================>.] - ETA: 0s - loss: 1.3287 - accuracy: 0.5226 3595/3595 [==============================] - 2s 504us/sample - loss: 1.3252 - accuracy: 0.5246 - val_loss: 1.2506 - val_accuracy: 0.5428 Epoch 7/30 32/3595 [..............................] - ETA: 1s - loss: 1.3096 - accuracy: 0.5312 160/3595 [>.............................] - ETA: 1s - loss: 1.3658 - accuracy: 0.4938 288/3595 [=>............................] - ETA: 1s - loss: 1.2517 - accuracy: 0.5347 416/3595 [==>...........................] - ETA: 1s - loss: 1.2531 - accuracy: 0.5505 544/3595 [===>..........................] - ETA: 1s - loss: 1.2672 - accuracy: 0.5533 672/3595 [====>.........................] - ETA: 1s - loss: 1.2612 - accuracy: 0.5551 832/3595 [=====>........................] - ETA: 1s - loss: 1.2746 - accuracy: 0.5421 960/3595 [=======>......................] - ETA: 1s - loss: 1.2880 - accuracy: 0.5312 1088/3595 [========>.....................] - ETA: 1s - loss: 1.2667 - accuracy: 0.5377 1216/3595 [=========>....................] - ETA: 1s - loss: 1.2634 - accuracy: 0.5403 1344/3595 [==========>...................] - ETA: 1s - loss: 1.2605 - accuracy: 0.5439 1472/3595 [===========>..................] - ETA: 1s - loss: 1.2627 - accuracy: 0.5435 1600/3595 [============>.................] - ETA: 0s - loss: 1.2571 - accuracy: 0.5481 1728/3595 [=============>................] - ETA: 0s - loss: 1.2558 - accuracy: 0.5469 1856/3595 [==============>...............] - ETA: 0s - loss: 1.2568 - accuracy: 0.5469 1984/3595 [===============>..............] - ETA: 0s - loss: 1.2569 - accuracy: 0.5494 2112/3595 [================>.............] - ETA: 0s - loss: 1.2538 - accuracy: 0.5492 2272/3595 [=================>............] - ETA: 0s - loss: 1.2545 - accuracy: 0.5467 2400/3595 [===================>..........] - ETA: 0s - loss: 1.2495 - accuracy: 0.5517 2528/3595 [====================>.........] - ETA: 0s - loss: 1.2506 - accuracy: 0.5502 2656/3595 [=====================>........] - ETA: 0s - loss: 1.2595 - accuracy: 0.5486 2784/3595 [======================>.......] - ETA: 0s - loss: 1.2542 - accuracy: 0.5499 2912/3595 [=======================>......] - ETA: 0s - loss: 1.2515 - accuracy: 0.5508 3040/3595 [========================>.....] - ETA: 0s - loss: 1.2475 - accuracy: 0.5523 3168/3595 [=========================>....] - ETA: 0s - loss: 1.2485 - accuracy: 0.5537 3296/3595 [==========================>...] - ETA: 0s - loss: 1.2479 - accuracy: 0.5537 3424/3595 [===========================>..] - ETA: 0s - loss: 1.2493 - accuracy: 0.5511 3552/3595 [============================>.] - ETA: 0s - loss: 1.2549 - accuracy: 0.5484 3595/3595 [==============================] - 2s 509us/sample - loss: 1.2561 - accuracy: 0.5477 - val_loss: 1.2072 - val_accuracy: 0.5473 Epoch 8/30 32/3595 [..............................] - ETA: 1s - loss: 1.1296 - accuracy: 0.6250 160/3595 [>.............................] - ETA: 1s - loss: 1.2789 - accuracy: 0.5437 288/3595 [=>............................] - ETA: 1s - loss: 1.2657 - accuracy: 0.5799 416/3595 [==>...........................] - ETA: 1s - loss: 1.2329 - accuracy: 0.5817 512/3595 [===>..........................] - ETA: 1s - loss: 1.2627 - accuracy: 0.5664 640/3595 [====>.........................] - ETA: 1s - loss: 1.2409 - accuracy: 0.5719 736/3595 [=====>........................] - ETA: 1s - loss: 1.2275 - accuracy: 0.5761 832/3595 [=====>........................] - ETA: 1s - loss: 1.2271 - accuracy: 0.5769 960/3595 [=======>......................] - ETA: 1s - loss: 1.2208 - accuracy: 0.5792 1056/3595 [=======>......................] - ETA: 1s - loss: 1.2315 - accuracy: 0.5720 1184/3595 [========>.....................] - ETA: 1s - loss: 1.2509 - accuracy: 0.5566 1312/3595 [=========>....................] - ETA: 1s - loss: 1.2426 - accuracy: 0.5572 1440/3595 [===========>..................] - ETA: 1s - loss: 1.2233 - accuracy: 0.5625 1568/3595 [============>.................] - ETA: 1s - loss: 1.2350 - accuracy: 0.5548 1696/3595 [=============>................] - ETA: 0s - loss: 1.2300 - accuracy: 0.5548 1824/3595 [==============>...............] - ETA: 0s - loss: 1.2212 - accuracy: 0.5554 1952/3595 [===============>..............] - ETA: 0s - loss: 1.2189 - accuracy: 0.5579 2080/3595 [================>.............] - ETA: 0s - loss: 1.2132 - accuracy: 0.5611 2208/3595 [=================>............] - ETA: 0s - loss: 1.2150 - accuracy: 0.5598 2368/3595 [==================>...........] - ETA: 0s - loss: 1.2147 - accuracy: 0.5600 2496/3595 [===================>..........] - ETA: 0s - loss: 1.2118 - accuracy: 0.5605 2624/3595 [====================>.........] - ETA: 0s - loss: 1.2157 - accuracy: 0.5602 2752/3595 [=====================>........] - ETA: 0s - loss: 1.2162 - accuracy: 0.5625 2880/3595 [=======================>......] - ETA: 0s - loss: 1.2103 - accuracy: 0.5642 3008/3595 [========================>.....] - ETA: 0s - loss: 1.2063 - accuracy: 0.5645 3168/3595 [=========================>....] - ETA: 0s - loss: 1.2077 - accuracy: 0.5631 3264/3595 [==========================>...] - ETA: 0s - loss: 1.2040 - accuracy: 0.5650 3392/3595 [===========================>..] - ETA: 0s - loss: 1.2037 - accuracy: 0.5640 3520/3595 [============================>.] - ETA: 0s - loss: 1.2100 - accuracy: 0.5619 3595/3595 [==============================] - 2s 529us/sample - loss: 1.2106 - accuracy: 0.5622 - val_loss: 1.1690 - val_accuracy: 0.5829 Epoch 9/30 32/3595 [..............................] - ETA: 1s - loss: 1.0957 - accuracy: 0.5625 160/3595 [>.............................] - ETA: 1s - loss: 1.1594 - accuracy: 0.5625 288/3595 [=>............................] - ETA: 1s - loss: 1.1962 - accuracy: 0.5625 416/3595 [==>...........................] - ETA: 1s - loss: 1.1497 - accuracy: 0.5817 544/3595 [===>..........................] - ETA: 1s - loss: 1.1701 - accuracy: 0.5643 672/3595 [====>.........................] - ETA: 1s - loss: 1.1641 - accuracy: 0.5625 800/3595 [=====>........................] - ETA: 1s - loss: 1.1542 - accuracy: 0.5713 928/3595 [======>.......................] - ETA: 1s - loss: 1.1702 - accuracy: 0.5647 1088/3595 [========>.....................] - ETA: 1s - loss: 1.1725 - accuracy: 0.5634 1216/3595 [=========>....................] - ETA: 1s - loss: 1.1731 - accuracy: 0.5609 1376/3595 [==========>...................] - ETA: 1s - loss: 1.1710 - accuracy: 0.5603 1504/3595 [===========>..................] - ETA: 0s - loss: 1.1763 - accuracy: 0.5612 1632/3595 [============>.................] - ETA: 0s - loss: 1.1782 - accuracy: 0.5625 1728/3595 [=============>................] - ETA: 0s - loss: 1.1735 - accuracy: 0.5648 1856/3595 [==============>...............] - ETA: 0s - loss: 1.1689 - accuracy: 0.5679 2016/3595 [===============>..............] - ETA: 0s - loss: 1.1771 - accuracy: 0.5675 2144/3595 [================>.............] - ETA: 0s - loss: 1.1632 - accuracy: 0.5760 2272/3595 [=================>............] - ETA: 0s - loss: 1.1617 - accuracy: 0.5753 2400/3595 [===================>..........] - ETA: 0s - loss: 1.1611 - accuracy: 0.5725 2528/3595 [====================>.........] - ETA: 0s - loss: 1.1643 - accuracy: 0.5748 2656/3595 [=====================>........] - ETA: 0s - loss: 1.1671 - accuracy: 0.5730 2816/3595 [======================>.......] - ETA: 0s - loss: 1.1613 - accuracy: 0.5785 2944/3595 [=======================>......] - ETA: 0s - loss: 1.1604 - accuracy: 0.5788 3072/3595 [========================>.....] - ETA: 0s - loss: 1.1599 - accuracy: 0.5781 3200/3595 [=========================>....] - ETA: 0s - loss: 1.1529 - accuracy: 0.5797 3328/3595 [==========================>...] - ETA: 0s - loss: 1.1569 - accuracy: 0.5781 3456/3595 [===========================>..] - ETA: 0s - loss: 1.1601 - accuracy: 0.5796 3584/3595 [============================>.] - ETA: 0s - loss: 1.1646 - accuracy: 0.5770 3595/3595 [==============================] - 2s 513us/sample - loss: 1.1627 - accuracy: 0.5780 - val_loss: 1.1431 - val_accuracy: 0.5907 Epoch 10/30 32/3595 [..............................] - ETA: 1s - loss: 1.1302 - accuracy: 0.5625 160/3595 [>.............................] - ETA: 1s - loss: 1.1944 - accuracy: 0.5312 288/3595 [=>............................] - ETA: 1s - loss: 1.1374 - accuracy: 0.5556 416/3595 [==>...........................] - ETA: 1s - loss: 1.1442 - accuracy: 0.5385 544/3595 [===>..........................] - ETA: 1s - loss: 1.0986 - accuracy: 0.5717 672/3595 [====>.........................] - ETA: 1s - loss: 1.0994 - accuracy: 0.5699 800/3595 [=====>........................] - ETA: 1s - loss: 1.0957 - accuracy: 0.5875 928/3595 [======>.......................] - ETA: 1s - loss: 1.0849 - accuracy: 0.5959 1056/3595 [=======>......................] - ETA: 1s - loss: 1.1024 - accuracy: 0.5928 1184/3595 [========>.....................] - ETA: 1s - loss: 1.0962 - accuracy: 0.5954 1312/3595 [=========>....................] - ETA: 1s - loss: 1.1010 - accuracy: 0.5945 1440/3595 [===========>..................] - ETA: 1s - loss: 1.0923 - accuracy: 0.5938 1568/3595 [============>.................] - ETA: 0s - loss: 1.0917 - accuracy: 0.5944 1696/3595 [=============>................] - ETA: 0s - loss: 1.0971 - accuracy: 0.5973 1824/3595 [==============>...............] - ETA: 0s - loss: 1.1077 - accuracy: 0.5921 1952/3595 [===============>..............] - ETA: 0s - loss: 1.1122 - accuracy: 0.5948 2080/3595 [================>.............] - ETA: 0s - loss: 1.1242 - accuracy: 0.5904 2208/3595 [=================>............] - ETA: 0s - loss: 1.1177 - accuracy: 0.5924 2336/3595 [==================>...........] - ETA: 0s - loss: 1.1208 - accuracy: 0.5873 2464/3595 [===================>..........] - ETA: 0s - loss: 1.1191 - accuracy: 0.5877 2592/3595 [====================>.........] - ETA: 0s - loss: 1.1182 - accuracy: 0.5891 2720/3595 [=====================>........] - ETA: 0s - loss: 1.1233 - accuracy: 0.5890 2848/3595 [======================>.......] - ETA: 0s - loss: 1.1163 - accuracy: 0.5923 3008/3595 [========================>.....] - ETA: 0s - loss: 1.1155 - accuracy: 0.5938 3136/3595 [=========================>....] - ETA: 0s - loss: 1.1160 - accuracy: 0.5909 3264/3595 [==========================>...] - ETA: 0s - loss: 1.1176 - accuracy: 0.5916 3392/3595 [===========================>..] - ETA: 0s - loss: 1.1181 - accuracy: 0.5917 3520/3595 [============================>.] - ETA: 0s - loss: 1.1130 - accuracy: 0.5943 3595/3595 [==============================] - 2s 517us/sample - loss: 1.1099 - accuracy: 0.5961 - val_loss: 1.1508 - val_accuracy: 0.5829 Epoch 11/30 32/3595 [..............................] - ETA: 1s - loss: 0.9349 - accuracy: 0.6562 128/3595 [>.............................] - ETA: 2s - loss: 1.0495 - accuracy: 0.5781 256/3595 [=>............................] - ETA: 1s - loss: 1.0712 - accuracy: 0.5938 352/3595 [=>............................] - ETA: 1s - loss: 1.1099 - accuracy: 0.5824 480/3595 [===>..........................] - ETA: 1s - loss: 1.1158 - accuracy: 0.6021 608/3595 [====>.........................] - ETA: 1s - loss: 1.1151 - accuracy: 0.6053 736/3595 [=====>........................] - ETA: 1s - loss: 1.1207 - accuracy: 0.5965 864/3595 [======>.......................] - ETA: 1s - loss: 1.1188 - accuracy: 0.5995 992/3595 [=======>......................] - ETA: 1s - loss: 1.1084 - accuracy: 0.5968 1152/3595 [========>.....................] - ETA: 1s - loss: 1.1120 - accuracy: 0.5946 1280/3595 [=========>....................] - ETA: 1s - loss: 1.1119 - accuracy: 0.5977 1408/3595 [==========>...................] - ETA: 1s - loss: 1.0995 - accuracy: 0.6044 1536/3595 [===========>..................] - ETA: 1s - loss: 1.0949 - accuracy: 0.6048 1664/3595 [============>.................] - ETA: 0s - loss: 1.0939 - accuracy: 0.6070 1792/3595 [=============>................] - ETA: 0s - loss: 1.0846 - accuracy: 0.6105 1920/3595 [===============>..............] - ETA: 0s - loss: 1.0965 - accuracy: 0.6057 2048/3595 [================>.............] - ETA: 0s - loss: 1.0999 - accuracy: 0.6060 2208/3595 [=================>............] - ETA: 0s - loss: 1.0931 - accuracy: 0.6051 2336/3595 [==================>...........] - ETA: 0s - loss: 1.0923 - accuracy: 0.6062 2464/3595 [===================>..........] - ETA: 0s - loss: 1.0934 - accuracy: 0.6047 2592/3595 [====================>.........] - ETA: 0s - loss: 1.0906 - accuracy: 0.6053 2720/3595 [=====================>........] - ETA: 0s - loss: 1.0864 - accuracy: 0.6081 2816/3595 [======================>.......] - ETA: 0s - loss: 1.0798 - accuracy: 0.6119 2944/3595 [=======================>......] - ETA: 0s - loss: 1.0733 - accuracy: 0.6138 3072/3595 [========================>.....] - ETA: 0s - loss: 1.0696 - accuracy: 0.6146 3200/3595 [=========================>....] - ETA: 0s - loss: 1.0716 - accuracy: 0.6141 3328/3595 [==========================>...] - ETA: 0s - loss: 1.0745 - accuracy: 0.6160 3456/3595 [===========================>..] - ETA: 0s - loss: 1.0717 - accuracy: 0.6186 3584/3595 [============================>.] - ETA: 0s - loss: 1.0752 - accuracy: 0.6186 3595/3595 [==============================] - 2s 522us/sample - loss: 1.0742 - accuracy: 0.6186 - val_loss: 1.0907 - val_accuracy: 0.6040 Epoch 12/30 32/3595 [..............................] - ETA: 1s - loss: 1.0990 - accuracy: 0.5625 160/3595 [>.............................] - ETA: 1s - loss: 0.9412 - accuracy: 0.6562 320/3595 [=>............................] - ETA: 1s - loss: 1.0163 - accuracy: 0.6438 448/3595 [==>...........................] - ETA: 1s - loss: 1.0472 - accuracy: 0.6250 576/3595 [===>..........................] - ETA: 1s - loss: 1.0731 - accuracy: 0.6163 704/3595 [====>.........................] - ETA: 1s - loss: 1.0700 - accuracy: 0.6136 832/3595 [=====>........................] - ETA: 1s - loss: 1.0635 - accuracy: 0.6226 960/3595 [=======>......................] - ETA: 1s - loss: 1.0706 - accuracy: 0.6187 1088/3595 [========>.....................] - ETA: 1s - loss: 1.0624 - accuracy: 0.6222 1216/3595 [=========>....................] - ETA: 1s - loss: 1.0546 - accuracy: 0.6275 1344/3595 [==========>...................] - ETA: 1s - loss: 1.0472 - accuracy: 0.6302 1472/3595 [===========>..................] - ETA: 1s - loss: 1.0454 - accuracy: 0.6311 1600/3595 [============>.................] - ETA: 0s - loss: 1.0395 - accuracy: 0.6325 1728/3595 [=============>................] - ETA: 0s - loss: 1.0370 - accuracy: 0.6354 1856/3595 [==============>...............] - ETA: 0s - loss: 1.0415 - accuracy: 0.6293 1984/3595 [===============>..............] - ETA: 0s - loss: 1.0356 - accuracy: 0.6316 2112/3595 [================>.............] - ETA: 0s - loss: 1.0317 - accuracy: 0.6312 2240/3595 [=================>............] - ETA: 0s - loss: 1.0311 - accuracy: 0.6313 2368/3595 [==================>...........] - ETA: 0s - loss: 1.0247 - accuracy: 0.6343 2496/3595 [===================>..........] - ETA: 0s - loss: 1.0238 - accuracy: 0.6350 2624/3595 [====================>.........] - ETA: 0s - loss: 1.0226 - accuracy: 0.6357 2752/3595 [=====================>........] - ETA: 0s - loss: 1.0203 - accuracy: 0.6363 2880/3595 [=======================>......] - ETA: 0s - loss: 1.0171 - accuracy: 0.6372 3008/3595 [========================>.....] - ETA: 0s - loss: 1.0181 - accuracy: 0.6393 3136/3595 [=========================>....] - ETA: 0s - loss: 1.0164 - accuracy: 0.6400 3264/3595 [==========================>...] - ETA: 0s - loss: 1.0144 - accuracy: 0.6409 3392/3595 [===========================>..] - ETA: 0s - loss: 1.0098 - accuracy: 0.6421 3520/3595 [============================>.] - ETA: 0s - loss: 1.0128 - accuracy: 0.6406 3595/3595 [==============================] - 2s 513us/sample - loss: 1.0164 - accuracy: 0.6392 - val_loss: 1.0848 - val_accuracy: 0.6129 Epoch 13/30 32/3595 [..............................] - ETA: 1s - loss: 0.9861 - accuracy: 0.5000 160/3595 [>.............................] - ETA: 1s - loss: 0.9710 - accuracy: 0.6250 288/3595 [=>............................] - ETA: 1s - loss: 0.9471 - accuracy: 0.6597 384/3595 [==>...........................] - ETA: 1s - loss: 0.9509 - accuracy: 0.6484 512/3595 [===>..........................] - ETA: 1s - loss: 0.9467 - accuracy: 0.6445 672/3595 [====>.........................] - ETA: 1s - loss: 0.9693 - accuracy: 0.6443 800/3595 [=====>........................] - ETA: 1s - loss: 0.9703 - accuracy: 0.6413 928/3595 [======>.......................] - ETA: 1s - loss: 0.9578 - accuracy: 0.6476 1056/3595 [=======>......................] - ETA: 1s - loss: 0.9845 - accuracy: 0.6411 1184/3595 [========>.....................] - ETA: 1s - loss: 0.9874 - accuracy: 0.6419 1312/3595 [=========>....................] - ETA: 1s - loss: 0.9804 - accuracy: 0.6463 1440/3595 [===========>..................] - ETA: 1s - loss: 0.9831 - accuracy: 0.6458 1568/3595 [============>.................] - ETA: 0s - loss: 0.9803 - accuracy: 0.6448 1696/3595 [=============>................] - ETA: 0s - loss: 0.9703 - accuracy: 0.6474 1824/3595 [==============>...............] - ETA: 0s - loss: 0.9740 - accuracy: 0.6464 1952/3595 [===============>..............] - ETA: 0s - loss: 0.9761 - accuracy: 0.6460 2080/3595 [================>.............] - ETA: 0s - loss: 0.9717 - accuracy: 0.6481 2208/3595 [=================>............] - ETA: 0s - loss: 0.9723 - accuracy: 0.6486 2336/3595 [==================>...........] - ETA: 0s - loss: 0.9686 - accuracy: 0.6494 2464/3595 [===================>..........] - ETA: 0s - loss: 0.9731 - accuracy: 0.6473 2592/3595 [====================>.........] - ETA: 0s - loss: 0.9757 - accuracy: 0.6474 2720/3595 [=====================>........] - ETA: 0s - loss: 0.9729 - accuracy: 0.6489 2848/3595 [======================>.......] - ETA: 0s - loss: 0.9747 - accuracy: 0.6489 2976/3595 [=======================>......] - ETA: 0s - loss: 0.9720 - accuracy: 0.6489 3136/3595 [=========================>....] - ETA: 0s - loss: 0.9767 - accuracy: 0.6483 3264/3595 [==========================>...] - ETA: 0s - loss: 0.9773 - accuracy: 0.6498 3360/3595 [===========================>..] - ETA: 0s - loss: 0.9832 - accuracy: 0.6482 3488/3595 [============================>.] - ETA: 0s - loss: 0.9835 - accuracy: 0.6471 3584/3595 [============================>.] - ETA: 0s - loss: 0.9864 - accuracy: 0.6445 3595/3595 [==============================] - 2s 526us/sample - loss: 0.9861 - accuracy: 0.6442 - val_loss: 1.0648 - val_accuracy: 0.6151 Epoch 14/30 32/3595 [..............................] - ETA: 1s - loss: 0.7964 - accuracy: 0.7188 160/3595 [>.............................] - ETA: 1s - loss: 1.2141 - accuracy: 0.5938 288/3595 [=>............................] - ETA: 1s - loss: 1.1340 - accuracy: 0.5972 416/3595 [==>...........................] - ETA: 1s - loss: 1.0992 - accuracy: 0.6106 576/3595 [===>..........................] - ETA: 1s - loss: 1.0677 - accuracy: 0.6128 704/3595 [====>.........................] - ETA: 1s - loss: 1.0477 - accuracy: 0.6179 832/3595 [=====>........................] - ETA: 1s - loss: 1.0394 - accuracy: 0.6298 960/3595 [=======>......................] - ETA: 1s - loss: 1.0359 - accuracy: 0.6281 1088/3595 [========>.....................] - ETA: 1s - loss: 1.0416 - accuracy: 0.6232 1216/3595 [=========>....................] - ETA: 1s - loss: 1.0283 - accuracy: 0.6316 1376/3595 [==========>...................] - ETA: 1s - loss: 1.0053 - accuracy: 0.6374 1504/3595 [===========>..................] - ETA: 0s - loss: 1.0041 - accuracy: 0.6376 1632/3595 [============>.................] - ETA: 0s - loss: 0.9923 - accuracy: 0.6415 1760/3595 [=============>................] - ETA: 0s - loss: 0.9908 - accuracy: 0.6426 1888/3595 [==============>...............] - ETA: 0s - loss: 0.9869 - accuracy: 0.6457 2016/3595 [===============>..............] - ETA: 0s - loss: 0.9849 - accuracy: 0.6493 2112/3595 [================>.............] - ETA: 0s - loss: 0.9882 - accuracy: 0.6477 2240/3595 [=================>............] - ETA: 0s - loss: 0.9885 - accuracy: 0.6482 2368/3595 [==================>...........] - ETA: 0s - loss: 0.9837 - accuracy: 0.6508 2496/3595 [===================>..........] - ETA: 0s - loss: 0.9837 - accuracy: 0.6502 2592/3595 [====================>.........] - ETA: 0s - loss: 0.9823 - accuracy: 0.6508 2752/3595 [=====================>........] - ETA: 0s - loss: 0.9743 - accuracy: 0.6519 2880/3595 [=======================>......] - ETA: 0s - loss: 0.9733 - accuracy: 0.6510 3008/3595 [========================>.....] - ETA: 0s - loss: 0.9736 - accuracy: 0.6513 3136/3595 [=========================>....] - ETA: 0s - loss: 0.9687 - accuracy: 0.6527 3264/3595 [==========================>...] - ETA: 0s - loss: 0.9633 - accuracy: 0.6556 3392/3595 [===========================>..] - ETA: 0s - loss: 0.9629 - accuracy: 0.6571 3520/3595 [============================>.] - ETA: 0s - loss: 0.9568 - accuracy: 0.6577 3595/3595 [==============================] - 2s 517us/sample - loss: 0.9573 - accuracy: 0.6567 - val_loss: 1.0845 - val_accuracy: 0.6151 Epoch 15/30 32/3595 [..............................] - ETA: 1s - loss: 1.0731 - accuracy: 0.5625 160/3595 [>.............................] - ETA: 1s - loss: 0.8521 - accuracy: 0.6875 320/3595 [=>............................] - ETA: 1s - loss: 0.9199 - accuracy: 0.6750 448/3595 [==>...........................] - ETA: 1s - loss: 0.9543 - accuracy: 0.6540 576/3595 [===>..........................] - ETA: 1s - loss: 0.9522 - accuracy: 0.6528 704/3595 [====>.........................] - ETA: 1s - loss: 0.9812 - accuracy: 0.6534 800/3595 [=====>........................] - ETA: 1s - loss: 0.9643 - accuracy: 0.6562 928/3595 [======>.......................] - ETA: 1s - loss: 0.9460 - accuracy: 0.6616 1088/3595 [========>.....................] - ETA: 1s - loss: 0.9593 - accuracy: 0.6608 1216/3595 [=========>....................] - ETA: 1s - loss: 0.9454 - accuracy: 0.6727 1344/3595 [==========>...................] - ETA: 1s - loss: 0.9597 - accuracy: 0.6682 1472/3595 [===========>..................] - ETA: 1s - loss: 0.9627 - accuracy: 0.6664 1600/3595 [============>.................] - ETA: 0s - loss: 0.9569 - accuracy: 0.6650 1728/3595 [=============>................] - ETA: 0s - loss: 0.9513 - accuracy: 0.6684 1856/3595 [==============>...............] - ETA: 0s - loss: 0.9526 - accuracy: 0.6633 1984/3595 [===============>..............] - ETA: 0s - loss: 0.9514 - accuracy: 0.6643 2112/3595 [================>.............] - ETA: 0s - loss: 0.9536 - accuracy: 0.6634 2240/3595 [=================>............] - ETA: 0s - loss: 0.9463 - accuracy: 0.6652 2368/3595 [==================>...........] - ETA: 0s - loss: 0.9461 - accuracy: 0.6655 2496/3595 [===================>..........] - ETA: 0s - loss: 0.9492 - accuracy: 0.6659 2624/3595 [====================>.........] - ETA: 0s - loss: 0.9471 - accuracy: 0.6669 2752/3595 [=====================>........] - ETA: 0s - loss: 0.9413 - accuracy: 0.6701 2880/3595 [=======================>......] - ETA: 0s - loss: 0.9404 - accuracy: 0.6708 3040/3595 [========================>.....] - ETA: 0s - loss: 0.9413 - accuracy: 0.6687 3168/3595 [=========================>....] - ETA: 0s - loss: 0.9455 - accuracy: 0.6660 3296/3595 [==========================>...] - ETA: 0s - loss: 0.9381 - accuracy: 0.6702 3424/3595 [===========================>..] - ETA: 0s - loss: 0.9475 - accuracy: 0.6662 3552/3595 [============================>.] - ETA: 0s - loss: 0.9472 - accuracy: 0.6661 3595/3595 [==============================] - 2s 513us/sample - loss: 0.9512 - accuracy: 0.6648 - val_loss: 1.0467 - val_accuracy: 0.6263 Epoch 16/30 32/3595 [..............................] - ETA: 1s - loss: 0.6350 - accuracy: 0.7500 160/3595 [>.............................] - ETA: 1s - loss: 0.8250 - accuracy: 0.6687 288/3595 [=>............................] - ETA: 1s - loss: 0.8352 - accuracy: 0.6667 416/3595 [==>...........................] - ETA: 1s - loss: 0.7976 - accuracy: 0.7115 544/3595 [===>..........................] - ETA: 1s - loss: 0.8085 - accuracy: 0.7096 672/3595 [====>.........................] - ETA: 1s - loss: 0.8243 - accuracy: 0.7054 800/3595 [=====>........................] - ETA: 1s - loss: 0.8372 - accuracy: 0.7025 928/3595 [======>.......................] - ETA: 1s - loss: 0.8411 - accuracy: 0.6972 1056/3595 [=======>......................] - ETA: 1s - loss: 0.8382 - accuracy: 0.7017 1184/3595 [========>.....................] - ETA: 1s - loss: 0.8550 - accuracy: 0.6917 1312/3595 [=========>....................] - ETA: 1s - loss: 0.8607 - accuracy: 0.6936 1440/3595 [===========>..................] - ETA: 1s - loss: 0.8825 - accuracy: 0.6896 1568/3595 [============>.................] - ETA: 0s - loss: 0.8829 - accuracy: 0.6920 1696/3595 [=============>................] - ETA: 0s - loss: 0.8821 - accuracy: 0.6940 1824/3595 [==============>...............] - ETA: 0s - loss: 0.8796 - accuracy: 0.6941 1952/3595 [===============>..............] - ETA: 0s - loss: 0.8773 - accuracy: 0.6942 2080/3595 [================>.............] - ETA: 0s - loss: 0.8687 - accuracy: 0.6971 2208/3595 [=================>............] - ETA: 0s - loss: 0.8705 - accuracy: 0.6947 2336/3595 [==================>...........] - ETA: 0s - loss: 0.8774 - accuracy: 0.6926 2464/3595 [===================>..........] - ETA: 0s - loss: 0.8744 - accuracy: 0.6948 2592/3595 [====================>.........] - ETA: 0s - loss: 0.8859 - accuracy: 0.6914 2752/3595 [=====================>........] - ETA: 0s - loss: 0.8871 - accuracy: 0.6922 2880/3595 [=======================>......] - ETA: 0s - loss: 0.8900 - accuracy: 0.6910 2976/3595 [=======================>......] - ETA: 0s - loss: 0.8930 - accuracy: 0.6912 3104/3595 [========================>.....] - ETA: 0s - loss: 0.8929 - accuracy: 0.6920 3232/3595 [=========================>....] - ETA: 0s - loss: 0.8898 - accuracy: 0.6934 3328/3595 [==========================>...] - ETA: 0s - loss: 0.8883 - accuracy: 0.6944 3488/3595 [============================>.] - ETA: 0s - loss: 0.8961 - accuracy: 0.6907 3595/3595 [==============================] - 2s 526us/sample - loss: 0.8959 - accuracy: 0.6907 - val_loss: 1.0432 - val_accuracy: 0.6196 Epoch 17/30 32/3595 [..............................] - ETA: 1s - loss: 0.8710 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 1s - loss: 0.8415 - accuracy: 0.7000 288/3595 [=>............................] - ETA: 1s - loss: 0.8672 - accuracy: 0.6701 416/3595 [==>...........................] - ETA: 1s - loss: 0.8882 - accuracy: 0.6707 544/3595 [===>..........................] - ETA: 1s - loss: 0.9037 - accuracy: 0.6618 672/3595 [====>.........................] - ETA: 1s - loss: 0.8774 - accuracy: 0.6711 800/3595 [=====>........................] - ETA: 1s - loss: 0.8749 - accuracy: 0.6725 928/3595 [======>.......................] - ETA: 1s - loss: 0.8707 - accuracy: 0.6724 1056/3595 [=======>......................] - ETA: 1s - loss: 0.8786 - accuracy: 0.6752 1184/3595 [========>.....................] - ETA: 1s - loss: 0.8671 - accuracy: 0.6824 1312/3595 [=========>....................] - ETA: 1s - loss: 0.8778 - accuracy: 0.6784 1440/3595 [===========>..................] - ETA: 1s - loss: 0.8851 - accuracy: 0.6764 1568/3595 [============>.................] - ETA: 0s - loss: 0.8838 - accuracy: 0.6786 1664/3595 [============>.................] - ETA: 0s - loss: 0.8775 - accuracy: 0.6809 1792/3595 [=============>................] - ETA: 0s - loss: 0.8845 - accuracy: 0.6786 1920/3595 [===============>..............] - ETA: 0s - loss: 0.8843 - accuracy: 0.6818 2048/3595 [================>.............] - ETA: 0s - loss: 0.8891 - accuracy: 0.6812 2176/3595 [=================>............] - ETA: 0s - loss: 0.8783 - accuracy: 0.6857 2304/3595 [==================>...........] - ETA: 0s - loss: 0.8804 - accuracy: 0.6866 2432/3595 [===================>..........] - ETA: 0s - loss: 0.8824 - accuracy: 0.6887 2592/3595 [====================>.........] - ETA: 0s - loss: 0.8806 - accuracy: 0.6875 2720/3595 [=====================>........] - ETA: 0s - loss: 0.8810 - accuracy: 0.6857 2848/3595 [======================>.......] - ETA: 0s - loss: 0.8822 - accuracy: 0.6871 2976/3595 [=======================>......] - ETA: 0s - loss: 0.8820 - accuracy: 0.6865 3104/3595 [========================>.....] - ETA: 0s - loss: 0.8796 - accuracy: 0.6878 3232/3595 [=========================>....] - ETA: 0s - loss: 0.8847 - accuracy: 0.6853 3360/3595 [===========================>..] - ETA: 0s - loss: 0.8896 - accuracy: 0.6848 3488/3595 [============================>.] - ETA: 0s - loss: 0.8920 - accuracy: 0.6829 3595/3595 [==============================] - 2s 517us/sample - loss: 0.8962 - accuracy: 0.6801 - val_loss: 1.0259 - val_accuracy: 0.6318 Epoch 18/30 32/3595 [..............................] - ETA: 3s - loss: 0.8008 - accuracy: 0.7500 192/3595 [>.............................] - ETA: 1s - loss: 0.9063 - accuracy: 0.6979 320/3595 [=>............................] - ETA: 1s - loss: 0.9100 - accuracy: 0.6938 448/3595 [==>...........................] - ETA: 1s - loss: 0.8823 - accuracy: 0.7076 608/3595 [====>.........................] - ETA: 1s - loss: 0.8814 - accuracy: 0.7072 736/3595 [=====>........................] - ETA: 1s - loss: 0.8562 - accuracy: 0.7228 864/3595 [======>.......................] - ETA: 1s - loss: 0.8432 - accuracy: 0.7222 992/3595 [=======>......................] - ETA: 1s - loss: 0.8515 - accuracy: 0.7198 1120/3595 [========>.....................] - ETA: 1s - loss: 0.8522 - accuracy: 0.7152 1248/3595 [=========>....................] - ETA: 1s - loss: 0.8752 - accuracy: 0.7059 1376/3595 [==========>...................] - ETA: 1s - loss: 0.8682 - accuracy: 0.7086 1504/3595 [===========>..................] - ETA: 1s - loss: 0.8645 - accuracy: 0.7081 1632/3595 [============>.................] - ETA: 0s - loss: 0.8628 - accuracy: 0.7083 1760/3595 [=============>................] - ETA: 0s - loss: 0.8643 - accuracy: 0.7057 1888/3595 [==============>...............] - ETA: 0s - loss: 0.8632 - accuracy: 0.7039 2016/3595 [===============>..............] - ETA: 0s - loss: 0.8614 - accuracy: 0.7049 2144/3595 [================>.............] - ETA: 0s - loss: 0.8567 - accuracy: 0.7071 2272/3595 [=================>............] - ETA: 0s - loss: 0.8559 - accuracy: 0.7086 2400/3595 [===================>..........] - ETA: 0s - loss: 0.8497 - accuracy: 0.7100 2528/3595 [====================>.........] - ETA: 0s - loss: 0.8515 - accuracy: 0.7089 2656/3595 [=====================>........] - ETA: 0s - loss: 0.8505 - accuracy: 0.7093 2784/3595 [======================>.......] - ETA: 0s - loss: 0.8505 - accuracy: 0.7094 2912/3595 [=======================>......] - ETA: 0s - loss: 0.8511 - accuracy: 0.7084 3040/3595 [========================>.....] - ETA: 0s - loss: 0.8462 - accuracy: 0.7115 3168/3595 [=========================>....] - ETA: 0s - loss: 0.8471 - accuracy: 0.7112 3296/3595 [==========================>...] - ETA: 0s - loss: 0.8431 - accuracy: 0.7109 3424/3595 [===========================>..] - ETA: 0s - loss: 0.8464 - accuracy: 0.7103 3552/3595 [============================>.] - ETA: 0s - loss: 0.8438 - accuracy: 0.7120 3595/3595 [==============================] - 2s 522us/sample - loss: 0.8438 - accuracy: 0.7124 - val_loss: 1.0056 - val_accuracy: 0.6440 Epoch 19/30 32/3595 [..............................] - ETA: 1s - loss: 0.8994 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 1s - loss: 0.8862 - accuracy: 0.7125 288/3595 [=>............................] - ETA: 1s - loss: 0.8240 - accuracy: 0.7326 416/3595 [==>...........................] - ETA: 1s - loss: 0.8008 - accuracy: 0.7332 544/3595 [===>..........................] - ETA: 1s - loss: 0.7883 - accuracy: 0.7463 672/3595 [====>.........................] - ETA: 1s - loss: 0.7819 - accuracy: 0.7515 800/3595 [=====>........................] - ETA: 1s - loss: 0.7857 - accuracy: 0.7525 928/3595 [======>.......................] - ETA: 1s - loss: 0.7925 - accuracy: 0.7500 1056/3595 [=======>......................] - ETA: 1s - loss: 0.8120 - accuracy: 0.7367 1216/3595 [=========>....................] - ETA: 1s - loss: 0.8401 - accuracy: 0.7253 1344/3595 [==========>...................] - ETA: 1s - loss: 0.8426 - accuracy: 0.7254 1472/3595 [===========>..................] - ETA: 1s - loss: 0.8421 - accuracy: 0.7269 1600/3595 [============>.................] - ETA: 0s - loss: 0.8341 - accuracy: 0.7300 1728/3595 [=============>................] - ETA: 0s - loss: 0.8392 - accuracy: 0.7240 1856/3595 [==============>...............] - ETA: 0s - loss: 0.8356 - accuracy: 0.7231 1984/3595 [===============>..............] - ETA: 0s - loss: 0.8441 - accuracy: 0.7157 2112/3595 [================>.............] - ETA: 0s - loss: 0.8427 - accuracy: 0.7173 2208/3595 [=================>............] - ETA: 0s - loss: 0.8385 - accuracy: 0.7178 2336/3595 [==================>...........] - ETA: 0s - loss: 0.8347 - accuracy: 0.7188 2432/3595 [===================>..........] - ETA: 0s - loss: 0.8341 - accuracy: 0.7167 2560/3595 [====================>.........] - ETA: 0s - loss: 0.8329 - accuracy: 0.7168 2688/3595 [=====================>........] - ETA: 0s - loss: 0.8316 - accuracy: 0.7169 2816/3595 [======================>.......] - ETA: 0s - loss: 0.8247 - accuracy: 0.7188 2944/3595 [=======================>......] - ETA: 0s - loss: 0.8248 - accuracy: 0.7177 3072/3595 [========================>.....] - ETA: 0s - loss: 0.8260 - accuracy: 0.7181 3232/3595 [=========================>....] - ETA: 0s - loss: 0.8208 - accuracy: 0.7200 3360/3595 [===========================>..] - ETA: 0s - loss: 0.8192 - accuracy: 0.7208 3488/3595 [============================>.] - ETA: 0s - loss: 0.8206 - accuracy: 0.7210 3595/3595 [==============================] - 2s 517us/sample - loss: 0.8224 - accuracy: 0.7188 - val_loss: 1.0173 - val_accuracy: 0.6374 Epoch 20/30 32/3595 [..............................] - ETA: 1s - loss: 0.4891 - accuracy: 0.8438 160/3595 [>.............................] - ETA: 1s - loss: 0.7297 - accuracy: 0.7750 288/3595 [=>............................] - ETA: 1s - loss: 0.7454 - accuracy: 0.7743 448/3595 [==>...........................] - ETA: 1s - loss: 0.7389 - accuracy: 0.7656 576/3595 [===>..........................] - ETA: 1s - loss: 0.7533 - accuracy: 0.7587 672/3595 [====>.........................] - ETA: 1s - loss: 0.7465 - accuracy: 0.7619 800/3595 [=====>........................] - ETA: 1s - loss: 0.7427 - accuracy: 0.7663 928/3595 [======>.......................] - ETA: 1s - loss: 0.7359 - accuracy: 0.7672 1056/3595 [=======>......................] - ETA: 1s - loss: 0.7379 - accuracy: 0.7633 1184/3595 [========>.....................] - ETA: 1s - loss: 0.7398 - accuracy: 0.7618 1280/3595 [=========>....................] - ETA: 1s - loss: 0.7447 - accuracy: 0.7563 1408/3595 [==========>...................] - ETA: 1s - loss: 0.7536 - accuracy: 0.7521 1568/3595 [============>.................] - ETA: 1s - loss: 0.7640 - accuracy: 0.7455 1696/3595 [=============>................] - ETA: 0s - loss: 0.7637 - accuracy: 0.7441 1824/3595 [==============>...............] - ETA: 0s - loss: 0.7599 - accuracy: 0.7434 1952/3595 [===============>..............] - ETA: 0s - loss: 0.7615 - accuracy: 0.7392 2080/3595 [================>.............] - ETA: 0s - loss: 0.7734 - accuracy: 0.7341 2208/3595 [=================>............] - ETA: 0s - loss: 0.7738 - accuracy: 0.7332 2368/3595 [==================>...........] - ETA: 0s - loss: 0.7714 - accuracy: 0.7340 2496/3595 [===================>..........] - ETA: 0s - loss: 0.7735 - accuracy: 0.7316 2624/3595 [====================>.........] - ETA: 0s - loss: 0.7802 - accuracy: 0.7287 2752/3595 [=====================>........] - ETA: 0s - loss: 0.7855 - accuracy: 0.7249 2880/3595 [=======================>......] - ETA: 0s - loss: 0.7844 - accuracy: 0.7247 3008/3595 [========================>.....] - ETA: 0s - loss: 0.7812 - accuracy: 0.7251 3136/3595 [=========================>....] - ETA: 0s - loss: 0.7829 - accuracy: 0.7248 3264/3595 [==========================>...] - ETA: 0s - loss: 0.7842 - accuracy: 0.7233 3392/3595 [===========================>..] - ETA: 0s - loss: 0.7852 - accuracy: 0.7238 3552/3595 [============================>.] - ETA: 0s - loss: 0.7812 - accuracy: 0.7261 3595/3595 [==============================] - 2s 517us/sample - loss: 0.7819 - accuracy: 0.7257 - val_loss: 1.0001 - val_accuracy: 0.6374 Epoch 21/30 32/3595 [..............................] - ETA: 1s - loss: 0.9929 - accuracy: 0.6250 160/3595 [>.............................] - ETA: 1s - loss: 0.8985 - accuracy: 0.6875 288/3595 [=>............................] - ETA: 1s - loss: 0.8457 - accuracy: 0.7118 448/3595 [==>...........................] - ETA: 1s - loss: 0.8343 - accuracy: 0.7031 576/3595 [===>..........................] - ETA: 1s - loss: 0.8137 - accuracy: 0.7135 704/3595 [====>.........................] - ETA: 1s - loss: 0.7803 - accuracy: 0.7330 832/3595 [=====>........................] - ETA: 1s - loss: 0.7923 - accuracy: 0.7224 960/3595 [=======>......................] - ETA: 1s - loss: 0.7807 - accuracy: 0.7302 1088/3595 [========>.....................] - ETA: 1s - loss: 0.7628 - accuracy: 0.7381 1216/3595 [=========>....................] - ETA: 1s - loss: 0.7593 - accuracy: 0.7418 1344/3595 [==========>...................] - ETA: 1s - loss: 0.7568 - accuracy: 0.7470 1472/3595 [===========>..................] - ETA: 1s - loss: 0.7633 - accuracy: 0.7439 1600/3595 [============>.................] - ETA: 0s - loss: 0.7661 - accuracy: 0.7406 1728/3595 [=============>................] - ETA: 0s - loss: 0.7605 - accuracy: 0.7425 1856/3595 [==============>...............] - ETA: 0s - loss: 0.7561 - accuracy: 0.7435 1984/3595 [===============>..............] - ETA: 0s - loss: 0.7597 - accuracy: 0.7424 2112/3595 [================>.............] - ETA: 0s - loss: 0.7534 - accuracy: 0.7410 2240/3595 [=================>............] - ETA: 0s - loss: 0.7463 - accuracy: 0.7429 2368/3595 [==================>...........] - ETA: 0s - loss: 0.7484 - accuracy: 0.7407 2496/3595 [===================>..........] - ETA: 0s - loss: 0.7469 - accuracy: 0.7420 2624/3595 [====================>.........] - ETA: 0s - loss: 0.7556 - accuracy: 0.7382 2752/3595 [=====================>........] - ETA: 0s - loss: 0.7598 - accuracy: 0.7355 2880/3595 [=======================>......] - ETA: 0s - loss: 0.7674 - accuracy: 0.7326 3008/3595 [========================>.....] - ETA: 0s - loss: 0.7694 - accuracy: 0.7307 3136/3595 [=========================>....] - ETA: 0s - loss: 0.7740 - accuracy: 0.7293 3296/3595 [==========================>...] - ETA: 0s - loss: 0.7691 - accuracy: 0.7306 3424/3595 [===========================>..] - ETA: 0s - loss: 0.7687 - accuracy: 0.7304 3552/3595 [============================>.] - ETA: 0s - loss: 0.7687 - accuracy: 0.7297 3595/3595 [==============================] - 2s 513us/sample - loss: 0.7686 - accuracy: 0.7296 - val_loss: 1.0208 - val_accuracy: 0.6418 Epoch 22/30 32/3595 [..............................] - ETA: 1s - loss: 0.8839 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 1s - loss: 0.7579 - accuracy: 0.7250 288/3595 [=>............................] - ETA: 1s - loss: 0.7275 - accuracy: 0.7396 416/3595 [==>...........................] - ETA: 1s - loss: 0.7431 - accuracy: 0.7356 544/3595 [===>..........................] - ETA: 1s - loss: 0.7449 - accuracy: 0.7390 672/3595 [====>.........................] - ETA: 1s - loss: 0.7428 - accuracy: 0.7396 800/3595 [=====>........................] - ETA: 1s - loss: 0.7557 - accuracy: 0.7325 928/3595 [======>.......................] - ETA: 1s - loss: 0.7493 - accuracy: 0.7328 1056/3595 [=======>......................] - ETA: 1s - loss: 0.7451 - accuracy: 0.7320 1184/3595 [========>.....................] - ETA: 1s - loss: 0.7496 - accuracy: 0.7280 1312/3595 [=========>....................] - ETA: 1s - loss: 0.7393 - accuracy: 0.7325 1440/3595 [===========>..................] - ETA: 1s - loss: 0.7504 - accuracy: 0.7299 1568/3595 [============>.................] - ETA: 0s - loss: 0.7482 - accuracy: 0.7302 1696/3595 [=============>................] - ETA: 0s - loss: 0.7464 - accuracy: 0.7323 1792/3595 [=============>................] - ETA: 0s - loss: 0.7451 - accuracy: 0.7344 1920/3595 [===============>..............] - ETA: 0s - loss: 0.7484 - accuracy: 0.7333 2016/3595 [===============>..............] - ETA: 0s - loss: 0.7440 - accuracy: 0.7371 2144/3595 [================>.............] - ETA: 0s - loss: 0.7424 - accuracy: 0.7388 2272/3595 [=================>............] - ETA: 0s - loss: 0.7354 - accuracy: 0.7403 2400/3595 [===================>..........] - ETA: 0s - loss: 0.7378 - accuracy: 0.7404 2528/3595 [====================>.........] - ETA: 0s - loss: 0.7374 - accuracy: 0.7417 2656/3595 [=====================>........] - ETA: 0s - loss: 0.7405 - accuracy: 0.7406 2784/3595 [======================>.......] - ETA: 0s - loss: 0.7391 - accuracy: 0.7425 2912/3595 [=======================>......] - ETA: 0s - loss: 0.7419 - accuracy: 0.7390 3072/3595 [========================>.....] - ETA: 0s - loss: 0.7394 - accuracy: 0.7406 3200/3595 [=========================>....] - ETA: 0s - loss: 0.7408 - accuracy: 0.7397 3328/3595 [==========================>...] - ETA: 0s - loss: 0.7347 - accuracy: 0.7431 3456/3595 [===========================>..] - ETA: 0s - loss: 0.7349 - accuracy: 0.7405 3584/3595 [============================>.] - ETA: 0s - loss: 0.7350 - accuracy: 0.7402 3595/3595 [==============================] - 2s 522us/sample - loss: 0.7350 - accuracy: 0.7405 - val_loss: 1.0211 - val_accuracy: 0.6396 Epoch 23/30 32/3595 [..............................] - ETA: 3s - loss: 0.7282 - accuracy: 0.8438 192/3595 [>.............................] - ETA: 1s - loss: 0.6255 - accuracy: 0.7969 288/3595 [=>............................] - ETA: 1s - loss: 0.6763 - accuracy: 0.7812 416/3595 [==>...........................] - ETA: 1s - loss: 0.6808 - accuracy: 0.7716 544/3595 [===>..........................] - ETA: 1s - loss: 0.7039 - accuracy: 0.7610 672/3595 [====>.........................] - ETA: 1s - loss: 0.7047 - accuracy: 0.7589 800/3595 [=====>........................] - ETA: 1s - loss: 0.7487 - accuracy: 0.7450 928/3595 [======>.......................] - ETA: 1s - loss: 0.7401 - accuracy: 0.7511 1088/3595 [========>.....................] - ETA: 1s - loss: 0.7342 - accuracy: 0.7537 1216/3595 [=========>....................] - ETA: 1s - loss: 0.7319 - accuracy: 0.7558 1344/3595 [==========>...................] - ETA: 1s - loss: 0.7254 - accuracy: 0.7567 1472/3595 [===========>..................] - ETA: 1s - loss: 0.7237 - accuracy: 0.7554 1600/3595 [============>.................] - ETA: 0s - loss: 0.7392 - accuracy: 0.7487 1728/3595 [=============>................] - ETA: 0s - loss: 0.7409 - accuracy: 0.7500 1856/3595 [==============>...............] - ETA: 0s - loss: 0.7363 - accuracy: 0.7500 1984/3595 [===============>..............] - ETA: 0s - loss: 0.7333 - accuracy: 0.7510 2144/3595 [================>.............] - ETA: 0s - loss: 0.7226 - accuracy: 0.7551 2272/3595 [=================>............] - ETA: 0s - loss: 0.7214 - accuracy: 0.7562 2400/3595 [===================>..........] - ETA: 0s - loss: 0.7168 - accuracy: 0.7558 2528/3595 [====================>.........] - ETA: 0s - loss: 0.7179 - accuracy: 0.7551 2656/3595 [=====================>........] - ETA: 0s - loss: 0.7181 - accuracy: 0.7545 2784/3595 [======================>.......] - ETA: 0s - loss: 0.7155 - accuracy: 0.7579 2944/3595 [=======================>......] - ETA: 0s - loss: 0.7237 - accuracy: 0.7548 3072/3595 [========================>.....] - ETA: 0s - loss: 0.7267 - accuracy: 0.7526 3200/3595 [=========================>....] - ETA: 0s - loss: 0.7310 - accuracy: 0.7516 3328/3595 [==========================>...] - ETA: 0s - loss: 0.7278 - accuracy: 0.7530 3456/3595 [===========================>..] - ETA: 0s - loss: 0.7276 - accuracy: 0.7520 3584/3595 [============================>.] - ETA: 0s - loss: 0.7262 - accuracy: 0.7533 3595/3595 [==============================] - 2s 513us/sample - loss: 0.7269 - accuracy: 0.7530 - val_loss: 0.9823 - val_accuracy: 0.6452 Epoch 24/30 32/3595 [..............................] - ETA: 1s - loss: 0.8494 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 2s - loss: 0.8166 - accuracy: 0.6938 320/3595 [=>............................] - ETA: 1s - loss: 0.7169 - accuracy: 0.7281 448/3595 [==>...........................] - ETA: 1s - loss: 0.7196 - accuracy: 0.7344 576/3595 [===>..........................] - ETA: 1s - loss: 0.7128 - accuracy: 0.7378 704/3595 [====>.........................] - ETA: 1s - loss: 0.7043 - accuracy: 0.7514 832/3595 [=====>........................] - ETA: 1s - loss: 0.7073 - accuracy: 0.7560 960/3595 [=======>......................] - ETA: 1s - loss: 0.6987 - accuracy: 0.7615 1088/3595 [========>.....................] - ETA: 1s - loss: 0.7042 - accuracy: 0.7564 1216/3595 [=========>....................] - ETA: 1s - loss: 0.7107 - accuracy: 0.7525 1344/3595 [==========>...................] - ETA: 1s - loss: 0.7158 - accuracy: 0.7500 1472/3595 [===========>..................] - ETA: 1s - loss: 0.7043 - accuracy: 0.7534 1600/3595 [============>.................] - ETA: 0s - loss: 0.7025 - accuracy: 0.7531 1728/3595 [=============>................] - ETA: 0s - loss: 0.7108 - accuracy: 0.7512 1856/3595 [==============>...............] - ETA: 0s - loss: 0.7123 - accuracy: 0.7516 2016/3595 [===============>..............] - ETA: 0s - loss: 0.7122 - accuracy: 0.7495 2144/3595 [================>.............] - ETA: 0s - loss: 0.7121 - accuracy: 0.7486 2272/3595 [=================>............] - ETA: 0s - loss: 0.7056 - accuracy: 0.7513 2400/3595 [===================>..........] - ETA: 0s - loss: 0.7091 - accuracy: 0.7508 2528/3595 [====================>.........] - ETA: 0s - loss: 0.7086 - accuracy: 0.7504 2656/3595 [=====================>........] - ETA: 0s - loss: 0.7129 - accuracy: 0.7489 2784/3595 [======================>.......] - ETA: 0s - loss: 0.7127 - accuracy: 0.7486 2912/3595 [=======================>......] - ETA: 0s - loss: 0.7165 - accuracy: 0.7455 3040/3595 [========================>.....] - ETA: 0s - loss: 0.7175 - accuracy: 0.7457 3168/3595 [=========================>....] - ETA: 0s - loss: 0.7165 - accuracy: 0.7462 3296/3595 [==========================>...] - ETA: 0s - loss: 0.7139 - accuracy: 0.7476 3424/3595 [===========================>..] - ETA: 0s - loss: 0.7155 - accuracy: 0.7465 3552/3595 [============================>.] - ETA: 0s - loss: 0.7113 - accuracy: 0.7486 3595/3595 [==============================] - 2s 513us/sample - loss: 0.7147 - accuracy: 0.7477 - val_loss: 0.9953 - val_accuracy: 0.6385 Epoch 25/30 32/3595 [..............................] - ETA: 1s - loss: 0.6582 - accuracy: 0.7812 160/3595 [>.............................] - ETA: 1s - loss: 0.6320 - accuracy: 0.7688 288/3595 [=>............................] - ETA: 1s - loss: 0.6832 - accuracy: 0.7500 384/3595 [==>...........................] - ETA: 1s - loss: 0.6884 - accuracy: 0.7500 544/3595 [===>..........................] - ETA: 1s - loss: 0.6880 - accuracy: 0.7500 672/3595 [====>.........................] - ETA: 1s - loss: 0.6842 - accuracy: 0.7560 800/3595 [=====>........................] - ETA: 1s - loss: 0.6677 - accuracy: 0.7650 928/3595 [======>.......................] - ETA: 1s - loss: 0.6715 - accuracy: 0.7608 1056/3595 [=======>......................] - ETA: 1s - loss: 0.6778 - accuracy: 0.7595 1184/3595 [========>.....................] - ETA: 1s - loss: 0.6722 - accuracy: 0.7627 1280/3595 [=========>....................] - ETA: 1s - loss: 0.6853 - accuracy: 0.7563 1408/3595 [==========>...................] - ETA: 1s - loss: 0.6931 - accuracy: 0.7607 1536/3595 [===========>..................] - ETA: 1s - loss: 0.6920 - accuracy: 0.7611 1664/3595 [============>.................] - ETA: 0s - loss: 0.6960 - accuracy: 0.7560 1760/3595 [=============>................] - ETA: 0s - loss: 0.6918 - accuracy: 0.7574 1920/3595 [===============>..............] - ETA: 0s - loss: 0.6850 - accuracy: 0.7594 2048/3595 [================>.............] - ETA: 0s - loss: 0.6884 - accuracy: 0.7583 2176/3595 [=================>............] - ETA: 0s - loss: 0.6955 - accuracy: 0.7560 2304/3595 [==================>...........] - ETA: 0s - loss: 0.6915 - accuracy: 0.7582 2432/3595 [===================>..........] - ETA: 0s - loss: 0.6993 - accuracy: 0.7549 2560/3595 [====================>.........] - ETA: 0s - loss: 0.6976 - accuracy: 0.7555 2688/3595 [=====================>........] - ETA: 0s - loss: 0.6985 - accuracy: 0.7560 2816/3595 [======================>.......] - ETA: 0s - loss: 0.6964 - accuracy: 0.7560 2944/3595 [=======================>......] - ETA: 0s - loss: 0.6900 - accuracy: 0.7582 3072/3595 [========================>.....] - ETA: 0s - loss: 0.6899 - accuracy: 0.7594 3232/3595 [=========================>....] - ETA: 0s - loss: 0.6873 - accuracy: 0.7618 3360/3595 [===========================>..] - ETA: 0s - loss: 0.6860 - accuracy: 0.7628 3488/3595 [============================>.] - ETA: 0s - loss: 0.6840 - accuracy: 0.7629 3595/3595 [==============================] - 2s 523us/sample - loss: 0.6875 - accuracy: 0.7616 - val_loss: 0.9827 - val_accuracy: 0.6541 Epoch 26/30 32/3595 [..............................] - ETA: 1s - loss: 0.7651 - accuracy: 0.7500 160/3595 [>.............................] - ETA: 1s - loss: 0.6072 - accuracy: 0.7937 288/3595 [=>............................] - ETA: 1s - loss: 0.6063 - accuracy: 0.7778 416/3595 [==>...........................] - ETA: 1s - loss: 0.5779 - accuracy: 0.8005 544/3595 [===>..........................] - ETA: 1s - loss: 0.6094 - accuracy: 0.7849 672/3595 [====>.........................] - ETA: 1s - loss: 0.6312 - accuracy: 0.7827 800/3595 [=====>........................] - ETA: 1s - loss: 0.6206 - accuracy: 0.7800 928/3595 [======>.......................] - ETA: 1s - loss: 0.6297 - accuracy: 0.7769 1056/3595 [=======>......................] - ETA: 1s - loss: 0.6312 - accuracy: 0.7756 1184/3595 [========>.....................] - ETA: 1s - loss: 0.6352 - accuracy: 0.7720 1344/3595 [==========>...................] - ETA: 1s - loss: 0.6586 - accuracy: 0.7634 1472/3595 [===========>..................] - ETA: 1s - loss: 0.6728 - accuracy: 0.7602 1600/3595 [============>.................] - ETA: 0s - loss: 0.6677 - accuracy: 0.7656 1728/3595 [=============>................] - ETA: 0s - loss: 0.6648 - accuracy: 0.7674 1856/3595 [==============>...............] - ETA: 0s - loss: 0.6671 - accuracy: 0.7672 2016/3595 [===============>..............] - ETA: 0s - loss: 0.6624 - accuracy: 0.7684 2144/3595 [================>.............] - ETA: 0s - loss: 0.6666 - accuracy: 0.7659 2272/3595 [=================>............] - ETA: 0s - loss: 0.6764 - accuracy: 0.7636 2400/3595 [===================>..........] - ETA: 0s - loss: 0.6692 - accuracy: 0.7679 2528/3595 [====================>.........] - ETA: 0s - loss: 0.6675 - accuracy: 0.7702 2688/3595 [=====================>........] - ETA: 0s - loss: 0.6633 - accuracy: 0.7708 2816/3595 [======================>.......] - ETA: 0s - loss: 0.6620 - accuracy: 0.7710 2944/3595 [=======================>......] - ETA: 0s - loss: 0.6629 - accuracy: 0.7704 3072/3595 [========================>.....] - ETA: 0s - loss: 0.6651 - accuracy: 0.7689 3200/3595 [=========================>....] - ETA: 0s - loss: 0.6599 - accuracy: 0.7713 3328/3595 [==========================>...] - ETA: 0s - loss: 0.6589 - accuracy: 0.7716 3456/3595 [===========================>..] - ETA: 0s - loss: 0.6545 - accuracy: 0.7731 3584/3595 [============================>.] - ETA: 0s - loss: 0.6522 - accuracy: 0.7740 3595/3595 [==============================] - 2s 504us/sample - loss: 0.6531 - accuracy: 0.7739 - val_loss: 0.9541 - val_accuracy: 0.6585 Epoch 27/30 32/3595 [..............................] - ETA: 1s - loss: 0.6089 - accuracy: 0.8125 160/3595 [>.............................] - ETA: 1s - loss: 0.5363 - accuracy: 0.8250 288/3595 [=>............................] - ETA: 1s - loss: 0.5448 - accuracy: 0.8160 416/3595 [==>...........................] - ETA: 1s - loss: 0.5617 - accuracy: 0.7957 544/3595 [===>..........................] - ETA: 1s - loss: 0.5642 - accuracy: 0.8051 672/3595 [====>.........................] - ETA: 1s - loss: 0.5649 - accuracy: 0.8095 800/3595 [=====>........................] - ETA: 1s - loss: 0.5965 - accuracy: 0.7937 928/3595 [======>.......................] - ETA: 1s - loss: 0.6023 - accuracy: 0.7909 1056/3595 [=======>......................] - ETA: 1s - loss: 0.6067 - accuracy: 0.7917 1184/3595 [========>.....................] - ETA: 1s - loss: 0.6286 - accuracy: 0.7812 1312/3595 [=========>....................] - ETA: 1s - loss: 0.6285 - accuracy: 0.7767 1440/3595 [===========>..................] - ETA: 1s - loss: 0.6303 - accuracy: 0.7736 1568/3595 [============>.................] - ETA: 0s - loss: 0.6422 - accuracy: 0.7679 1696/3595 [=============>................] - ETA: 0s - loss: 0.6314 - accuracy: 0.7724 1824/3595 [==============>...............] - ETA: 0s - loss: 0.6247 - accuracy: 0.7741 1984/3595 [===============>..............] - ETA: 0s - loss: 0.6373 - accuracy: 0.7702 2112/3595 [================>.............] - ETA: 0s - loss: 0.6373 - accuracy: 0.7699 2240/3595 [=================>............] - ETA: 0s - loss: 0.6349 - accuracy: 0.7719 2368/3595 [==================>...........] - ETA: 0s - loss: 0.6326 - accuracy: 0.7720 2496/3595 [===================>..........] - ETA: 0s - loss: 0.6414 - accuracy: 0.7696 2624/3595 [====================>.........] - ETA: 0s - loss: 0.6385 - accuracy: 0.7713 2752/3595 [=====================>........] - ETA: 0s - loss: 0.6356 - accuracy: 0.7733 2880/3595 [=======================>......] - ETA: 0s - loss: 0.6360 - accuracy: 0.7726 3008/3595 [========================>.....] - ETA: 0s - loss: 0.6412 - accuracy: 0.7729 3136/3595 [=========================>....] - ETA: 0s - loss: 0.6458 - accuracy: 0.7698 3264/3595 [==========================>...] - ETA: 0s - loss: 0.6436 - accuracy: 0.7708 3392/3595 [===========================>..] - ETA: 0s - loss: 0.6408 - accuracy: 0.7739 3520/3595 [============================>.] - ETA: 0s - loss: 0.6391 - accuracy: 0.7741 3595/3595 [==============================] - 2s 514us/sample - loss: 0.6380 - accuracy: 0.7744 - val_loss: 0.9777 - val_accuracy: 0.6618 Epoch 28/30 32/3595 [..............................] - ETA: 1s - loss: 0.7394 - accuracy: 0.7500 160/3595 [>.............................] - ETA: 1s - loss: 0.6335 - accuracy: 0.7812 256/3595 [=>............................] - ETA: 1s - loss: 0.6105 - accuracy: 0.7852 416/3595 [==>...........................] - ETA: 1s - loss: 0.6266 - accuracy: 0.7788 544/3595 [===>..........................] - ETA: 1s - loss: 0.6107 - accuracy: 0.7794 672/3595 [====>.........................] - ETA: 1s - loss: 0.6011 - accuracy: 0.7783 768/3595 [=====>........................] - ETA: 1s - loss: 0.5981 - accuracy: 0.7839 896/3595 [======>.......................] - ETA: 1s - loss: 0.5890 - accuracy: 0.7946 992/3595 [=======>......................] - ETA: 1s - loss: 0.5982 - accuracy: 0.7893 1120/3595 [========>.....................] - ETA: 1s - loss: 0.6087 - accuracy: 0.7875 1248/3595 [=========>....................] - ETA: 1s - loss: 0.6049 - accuracy: 0.7885 1344/3595 [==========>...................] - ETA: 1s - loss: 0.6005 - accuracy: 0.7902 1472/3595 [===========>..................] - ETA: 1s - loss: 0.6084 - accuracy: 0.7901 1632/3595 [============>.................] - ETA: 0s - loss: 0.6123 - accuracy: 0.7880 1760/3595 [=============>................] - ETA: 0s - loss: 0.6210 - accuracy: 0.7830 1888/3595 [==============>...............] - ETA: 0s - loss: 0.6188 - accuracy: 0.7839 2016/3595 [===============>..............] - ETA: 0s - loss: 0.6186 - accuracy: 0.7842 2144/3595 [================>.............] - ETA: 0s - loss: 0.6221 - accuracy: 0.7826 2272/3595 [=================>............] - ETA: 0s - loss: 0.6246 - accuracy: 0.7790 2400/3595 [===================>..........] - ETA: 0s - loss: 0.6241 - accuracy: 0.7804 2528/3595 [====================>.........] - ETA: 0s - loss: 0.6197 - accuracy: 0.7812 2656/3595 [=====================>........] - ETA: 0s - loss: 0.6177 - accuracy: 0.7820 2816/3595 [======================>.......] - ETA: 0s - loss: 0.6141 - accuracy: 0.7827 2944/3595 [=======================>......] - ETA: 0s - loss: 0.6175 - accuracy: 0.7812 3072/3595 [========================>.....] - ETA: 0s - loss: 0.6170 - accuracy: 0.7819 3168/3595 [=========================>....] - ETA: 0s - loss: 0.6164 - accuracy: 0.7819 3296/3595 [==========================>...] - ETA: 0s - loss: 0.6194 - accuracy: 0.7816 3424/3595 [===========================>..] - ETA: 0s - loss: 0.6210 - accuracy: 0.7815 3552/3595 [============================>.] - ETA: 0s - loss: 0.6183 - accuracy: 0.7838 3595/3595 [==============================] - 2s 531us/sample - loss: 0.6201 - accuracy: 0.7830 - val_loss: 0.9885 - val_accuracy: 0.6541 Epoch 29/30 32/3595 [..............................] - ETA: 1s - loss: 0.5850 - accuracy: 0.7500 160/3595 [>.............................] - ETA: 1s - loss: 0.5922 - accuracy: 0.7937 320/3595 [=>............................] - ETA: 1s - loss: 0.5438 - accuracy: 0.8156 448/3595 [==>...........................] - ETA: 1s - loss: 0.5754 - accuracy: 0.8013 576/3595 [===>..........................] - ETA: 1s - loss: 0.5631 - accuracy: 0.8038 704/3595 [====>.........................] - ETA: 1s - loss: 0.5534 - accuracy: 0.8068 832/3595 [=====>........................] - ETA: 1s - loss: 0.5785 - accuracy: 0.8041 960/3595 [=======>......................] - ETA: 1s - loss: 0.5728 - accuracy: 0.8104 1088/3595 [========>.....................] - ETA: 1s - loss: 0.5691 - accuracy: 0.8125 1216/3595 [=========>....................] - ETA: 1s - loss: 0.5712 - accuracy: 0.8125 1344/3595 [==========>...................] - ETA: 1s - loss: 0.5728 - accuracy: 0.8088 1472/3595 [===========>..................] - ETA: 1s - loss: 0.5946 - accuracy: 0.8023 1600/3595 [============>.................] - ETA: 0s - loss: 0.5865 - accuracy: 0.8062 1728/3595 [=============>................] - ETA: 0s - loss: 0.5917 - accuracy: 0.8038 1856/3595 [==============>...............] - ETA: 0s - loss: 0.5901 - accuracy: 0.8033 1984/3595 [===============>..............] - ETA: 0s - loss: 0.5871 - accuracy: 0.8034 2112/3595 [================>.............] - ETA: 0s - loss: 0.5893 - accuracy: 0.8035 2240/3595 [=================>............] - ETA: 0s - loss: 0.5909 - accuracy: 0.8018 2400/3595 [===================>..........] - ETA: 0s - loss: 0.5890 - accuracy: 0.8012 2560/3595 [====================>.........] - ETA: 0s - loss: 0.5981 - accuracy: 0.7969 2688/3595 [=====================>........] - ETA: 0s - loss: 0.6045 - accuracy: 0.7935 2816/3595 [======================>.......] - ETA: 0s - loss: 0.6017 - accuracy: 0.7955 2944/3595 [=======================>......] - ETA: 0s - loss: 0.6025 - accuracy: 0.7965 3072/3595 [========================>.....] - ETA: 0s - loss: 0.6040 - accuracy: 0.7952 3200/3595 [=========================>....] - ETA: 0s - loss: 0.6033 - accuracy: 0.7931 3328/3595 [==========================>...] - ETA: 0s - loss: 0.6014 - accuracy: 0.7936 3456/3595 [===========================>..] - ETA: 0s - loss: 0.5987 - accuracy: 0.7948 3584/3595 [============================>.] - ETA: 0s - loss: 0.5992 - accuracy: 0.7946 3595/3595 [==============================] - 2s 509us/sample - loss: 0.5994 - accuracy: 0.7947 - val_loss: 0.9948 - val_accuracy: 0.6507 Epoch 30/30 32/3595 [..............................] - ETA: 1s - loss: 0.6193 - accuracy: 0.9062 160/3595 [>.............................] - ETA: 1s - loss: 0.6507 - accuracy: 0.8000 288/3595 [=>............................] - ETA: 1s - loss: 0.6296 - accuracy: 0.7986 448/3595 [==>...........................] - ETA: 1s - loss: 0.6127 - accuracy: 0.8058 608/3595 [====>.........................] - ETA: 1s - loss: 0.6188 - accuracy: 0.7977 736/3595 [=====>........................] - ETA: 1s - loss: 0.6098 - accuracy: 0.8003 864/3595 [======>.......................] - ETA: 1s - loss: 0.6130 - accuracy: 0.7998 992/3595 [=======>......................] - ETA: 1s - loss: 0.6224 - accuracy: 0.7944 1120/3595 [========>.....................] - ETA: 1s - loss: 0.6336 - accuracy: 0.7946 1248/3595 [=========>....................] - ETA: 1s - loss: 0.6321 - accuracy: 0.7909 1376/3595 [==========>...................] - ETA: 1s - loss: 0.6190 - accuracy: 0.7943 1504/3595 [===========>..................] - ETA: 0s - loss: 0.6132 - accuracy: 0.7932 1632/3595 [============>.................] - ETA: 0s - loss: 0.6097 - accuracy: 0.7953 1760/3595 [=============>................] - ETA: 0s - loss: 0.6074 - accuracy: 0.7972 1888/3595 [==============>...............] - ETA: 0s - loss: 0.6089 - accuracy: 0.7956 2016/3595 [===============>..............] - ETA: 0s - loss: 0.6049 - accuracy: 0.7981 2144/3595 [================>.............] - ETA: 0s - loss: 0.6003 - accuracy: 0.7985 2272/3595 [=================>............] - ETA: 0s - loss: 0.5975 - accuracy: 0.7993 2400/3595 [===================>..........] - ETA: 0s - loss: 0.6020 - accuracy: 0.7967 2528/3595 [====================>.........] - ETA: 0s - loss: 0.6122 - accuracy: 0.7903 2656/3595 [=====================>........] - ETA: 0s - loss: 0.6139 - accuracy: 0.7903 2784/3595 [======================>.......] - ETA: 0s - loss: 0.6099 - accuracy: 0.7909 2912/3595 [=======================>......] - ETA: 0s - loss: 0.6039 - accuracy: 0.7929 3040/3595 [========================>.....] - ETA: 0s - loss: 0.6003 - accuracy: 0.7947 3168/3595 [=========================>....] - ETA: 0s - loss: 0.5990 - accuracy: 0.7939 3328/3595 [==========================>...] - ETA: 0s - loss: 0.5977 - accuracy: 0.7954 3456/3595 [===========================>..] - ETA: 0s - loss: 0.5971 - accuracy: 0.7951 3584/3595 [============================>.] - ETA: 0s - loss: 0.5919 - accuracy: 0.7960 3595/3595 [==============================] - 2s 513us/sample - loss: 0.5918 - accuracy: 0.7964 - val_loss: 0.9465 - val_accuracy: 0.6641 1498/1498 - 0s - loss: 0.9259 - accuracy: 0.6756 Test accuracy: 0.67556745
And then I found this model accuracy was not ideal enough, so I then directly to process features_3_sec data file and use fcnn(fully connected neural network) to train. And I split data into training data(70%), valid data(20%) and test data(10%).
You can run the "python main.py FCNN1 --write_data True" in the terminal of Pycharm.(Warning: the right Virtual environment should be venv_python3.6) And you will get result as below shown.
Or you can directly run ! python main.py FCNN1 --write_data True in the jupyter notebook
! python main.py FCNN1 --write_data True
Columns with NA values are [] which means there is no missing value! Dataset is being processed right now...... Train set has 6993 records out of 9990 which is 70% Dev set has 1978 records out of 9990 which is 20% Test set has 1019 records out of 9990 which is 10% Model: "sequential" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= dense (Dense) (None, 256) 14848 _________________________________________________________________ dense_1 (Dense) (None, 128) 32896 _________________________________________________________________ dense_2 (Dense) (None, 64) 8256 _________________________________________________________________ dense_3 (Dense) (None, 10) 650 ================================================================= Total params: 56,650 Trainable params: 56,650 Non-trainable params: 0 _________________________________________________________________ Train on 6993 samples, validate on 1978 samples Epoch 1/70 128/6993 [..............................] - ETA: 16s - loss: 2.4324 - accuracy: 0.0625 2944/6993 [===========>..................] - ETA: 0s - loss: 1.8447 - accuracy: 0.3478 6400/6993 [==========================>...] - ETA: 0s - loss: 1.5232 - accuracy: 0.4569
2022-04-11 23:12:43.820341: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll 2022-04-11 23:12:49.868419: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 2022-04-11 23:12:49.873070: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll 2022-04-11 23:12:49.966206: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:12:49.966230: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:12:49.971233: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:12:50.621240: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:12:50.621261: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:12:50.621266: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:12:50.629158: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) WARNING:tensorflow:From D:\Programs\Anaconda_app\envs\comp47650_env\lib\site-packages\tensorflow_core\python\ops\resource_variable_ops.py:1630: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version. Instructions for updating: If using Keras pass *_constraint arguments to layers. 2022-04-11 23:12:51.050001: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll 2022-04-11 23:13:05.742302: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:13:05.742327: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:13:05.748300: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:13:05.774987: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:13:05.775011: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:13:05.780944: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:13:05.781014: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:13:05.781025: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:13:05.781031: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:13:05.787003: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) 2022-04-11 23:13:06.153492: W tensorflow/python/util/util.cc:299] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them.
6993/6993 [==============================] - 1s 74us/sample - loss: 1.4861 - accuracy: 0.4710 - val_loss: 1.0799 - val_accuracy: 0.6213 Epoch 2/70 128/6993 [..............................] - ETA: 0s - loss: 0.8891 - accuracy: 0.6953 2944/6993 [===========>..................] - ETA: 0s - loss: 0.9648 - accuracy: 0.6712 6144/6993 [=========================>....] - ETA: 0s - loss: 0.9174 - accuracy: 0.6862 6993/6993 [==============================] - 0s 25us/sample - loss: 0.9098 - accuracy: 0.6900 - val_loss: 0.8380 - val_accuracy: 0.7139 Epoch 3/70 128/6993 [..............................] - ETA: 0s - loss: 0.8193 - accuracy: 0.7422 2944/6993 [===========>..................] - ETA: 0s - loss: 0.7263 - accuracy: 0.7649 6016/6993 [========================>.....] - ETA: 0s - loss: 0.7087 - accuracy: 0.7678 6993/6993 [==============================] - 0s 25us/sample - loss: 0.7027 - accuracy: 0.7681 - val_loss: 0.7158 - val_accuracy: 0.7457 Epoch 4/70 128/6993 [..............................] - ETA: 0s - loss: 0.5787 - accuracy: 0.7969 2816/6993 [===========>..................] - ETA: 0s - loss: 0.6021 - accuracy: 0.8018 6016/6993 [========================>.....] - ETA: 0s - loss: 0.5779 - accuracy: 0.8097 6993/6993 [==============================] - 0s 25us/sample - loss: 0.5767 - accuracy: 0.8081 - val_loss: 0.6561 - val_accuracy: 0.7700 Epoch 5/70 128/6993 [..............................] - ETA: 0s - loss: 0.3706 - accuracy: 0.8672 2816/6993 [===========>..................] - ETA: 0s - loss: 0.4839 - accuracy: 0.8459 6016/6993 [========================>.....] - ETA: 0s - loss: 0.4860 - accuracy: 0.8447 6993/6993 [==============================] - 0s 25us/sample - loss: 0.4862 - accuracy: 0.8431 - val_loss: 0.5961 - val_accuracy: 0.7942 Epoch 6/70 128/6993 [..............................] - ETA: 0s - loss: 0.4873 - accuracy: 0.8438 2816/6993 [===========>..................] - ETA: 0s - loss: 0.4261 - accuracy: 0.8643 6144/6993 [=========================>....] - ETA: 0s - loss: 0.4212 - accuracy: 0.8607 6993/6993 [==============================] - 0s 25us/sample - loss: 0.4212 - accuracy: 0.8606 - val_loss: 0.5533 - val_accuracy: 0.8038 Epoch 7/70 128/6993 [..............................] - ETA: 0s - loss: 0.3538 - accuracy: 0.8672 3072/6993 [============>.................] - ETA: 0s - loss: 0.3562 - accuracy: 0.8864 6144/6993 [=========================>....] - ETA: 0s - loss: 0.3584 - accuracy: 0.8861 6993/6993 [==============================] - 0s 25us/sample - loss: 0.3539 - accuracy: 0.8873 - val_loss: 0.5019 - val_accuracy: 0.8311 Epoch 8/70 128/6993 [..............................] - ETA: 0s - loss: 0.3056 - accuracy: 0.9062 2944/6993 [===========>..................] - ETA: 0s - loss: 0.2896 - accuracy: 0.9117 6144/6993 [=========================>....] - ETA: 0s - loss: 0.3021 - accuracy: 0.9079 6993/6993 [==============================] - 0s 25us/sample - loss: 0.3037 - accuracy: 0.9063 - val_loss: 0.4823 - val_accuracy: 0.8327 Epoch 9/70 128/6993 [..............................] - ETA: 0s - loss: 0.2544 - accuracy: 0.9297 2944/6993 [===========>..................] - ETA: 0s - loss: 0.2464 - accuracy: 0.9297 6016/6993 [========================>.....] - ETA: 0s - loss: 0.2565 - accuracy: 0.9235 6993/6993 [==============================] - 0s 25us/sample - loss: 0.2554 - accuracy: 0.9234 - val_loss: 0.4523 - val_accuracy: 0.8448 Epoch 10/70 128/6993 [..............................] - ETA: 0s - loss: 0.2352 - accuracy: 0.9141 2816/6993 [===========>..................] - ETA: 0s - loss: 0.2147 - accuracy: 0.9354 6016/6993 [========================>.....] - ETA: 0s - loss: 0.2220 - accuracy: 0.9328 6993/6993 [==============================] - 0s 25us/sample - loss: 0.2222 - accuracy: 0.9309 - val_loss: 0.4360 - val_accuracy: 0.8418 Epoch 11/70 128/6993 [..............................] - ETA: 0s - loss: 0.2066 - accuracy: 0.9375 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1922 - accuracy: 0.9431 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1853 - accuracy: 0.9446 6993/6993 [==============================] - 0s 25us/sample - loss: 0.1876 - accuracy: 0.9458 - val_loss: 0.4345 - val_accuracy: 0.8509 Epoch 12/70 128/6993 [..............................] - ETA: 0s - loss: 0.1500 - accuracy: 0.9453 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1658 - accuracy: 0.9520 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1575 - accuracy: 0.9563 6993/6993 [==============================] - 0s 25us/sample - loss: 0.1599 - accuracy: 0.9550 - val_loss: 0.4203 - val_accuracy: 0.8574 Epoch 13/70 128/6993 [..............................] - ETA: 0s - loss: 0.1035 - accuracy: 0.9766 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1144 - accuracy: 0.9757 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1304 - accuracy: 0.9698 6784/6993 [============================>.] - ETA: 0s - loss: 0.1354 - accuracy: 0.9673 6993/6993 [==============================] - 0s 34us/sample - loss: 0.1358 - accuracy: 0.9668 - val_loss: 0.4203 - val_accuracy: 0.8605 Epoch 14/70 128/6993 [..............................] - ETA: 0s - loss: 0.1185 - accuracy: 0.9609 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1125 - accuracy: 0.9730 3328/6993 [=============>................] - ETA: 0s - loss: 0.1059 - accuracy: 0.9748 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1141 - accuracy: 0.9721 6993/6993 [==============================] - 0s 34us/sample - loss: 0.1175 - accuracy: 0.9695 - val_loss: 0.4195 - val_accuracy: 0.8645 Epoch 15/70 128/6993 [..............................] - ETA: 0s - loss: 0.1007 - accuracy: 0.9688 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0982 - accuracy: 0.9771 3968/6993 [================>.............] - ETA: 0s - loss: 0.0976 - accuracy: 0.9788 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0961 - accuracy: 0.9781 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0983 - accuracy: 0.9767 - val_loss: 0.4077 - val_accuracy: 0.8670 Epoch 16/70 128/6993 [..............................] - ETA: 0s - loss: 0.0559 - accuracy: 1.0000 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0792 - accuracy: 0.9840 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0796 - accuracy: 0.9828 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0789 - accuracy: 0.9834 - val_loss: 0.4159 - val_accuracy: 0.8680 Epoch 17/70 128/6993 [..............................] - ETA: 0s - loss: 0.0642 - accuracy: 0.9922 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0649 - accuracy: 0.9877 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0723 - accuracy: 0.9840 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0729 - accuracy: 0.9838 - val_loss: 0.4217 - val_accuracy: 0.8675 Epoch 18/70 128/6993 [..............................] - ETA: 0s - loss: 0.0490 - accuracy: 0.9922 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0637 - accuracy: 0.9863 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0608 - accuracy: 0.9882 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0643 - accuracy: 0.9867 - val_loss: 0.4210 - val_accuracy: 0.8640 Epoch 19/70 128/6993 [..............................] - ETA: 0s - loss: 0.0513 - accuracy: 1.0000 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0536 - accuracy: 0.9901 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0567 - accuracy: 0.9891 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0558 - accuracy: 0.9894 - val_loss: 0.4122 - val_accuracy: 0.8711 Epoch 20/70 128/6993 [..............................] - ETA: 0s - loss: 0.0398 - accuracy: 0.9922 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0455 - accuracy: 0.9943 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0436 - accuracy: 0.9943 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0432 - accuracy: 0.9937 - val_loss: 0.4081 - val_accuracy: 0.8741 Epoch 21/70 128/6993 [..............................] - ETA: 0s - loss: 0.0302 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0356 - accuracy: 0.9954 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0353 - accuracy: 0.9943 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0365 - accuracy: 0.9940 - val_loss: 0.4087 - val_accuracy: 0.8741 Epoch 22/70 128/6993 [..............................] - ETA: 0s - loss: 0.0183 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0286 - accuracy: 0.9953 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0302 - accuracy: 0.9963 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0308 - accuracy: 0.9963 - val_loss: 0.4055 - val_accuracy: 0.8822 Epoch 23/70 128/6993 [..............................] - ETA: 0s - loss: 0.0204 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0206 - accuracy: 0.9988 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0223 - accuracy: 0.9987 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0229 - accuracy: 0.9981 - val_loss: 0.4063 - val_accuracy: 0.8837 Epoch 24/70 128/6993 [..............................] - ETA: 0s - loss: 0.0192 - accuracy: 0.9922 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0185 - accuracy: 0.9989 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0196 - accuracy: 0.9986 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0198 - accuracy: 0.9984 - val_loss: 0.4103 - val_accuracy: 0.8847 Epoch 25/70 128/6993 [..............................] - ETA: 0s - loss: 0.0504 - accuracy: 0.9922 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0187 - accuracy: 0.9982 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0192 - accuracy: 0.9977 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0191 - accuracy: 0.9979 - val_loss: 0.4226 - val_accuracy: 0.8802 Epoch 26/70 128/6993 [..............................] - ETA: 0s - loss: 0.0294 - accuracy: 0.9922 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0198 - accuracy: 0.9974 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0203 - accuracy: 0.9975 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0208 - accuracy: 0.9974 - val_loss: 0.4175 - val_accuracy: 0.8852 Epoch 27/70 128/6993 [..............................] - ETA: 0s - loss: 0.0099 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0142 - accuracy: 0.9996 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0135 - accuracy: 0.9994 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0146 - accuracy: 0.9990 - val_loss: 0.4080 - val_accuracy: 0.8878 Epoch 28/70 128/6993 [..............................] - ETA: 0s - loss: 0.0074 - accuracy: 1.0000 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0117 - accuracy: 0.9990 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0122 - accuracy: 0.9991 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0126 - accuracy: 0.9989 - val_loss: 0.4287 - val_accuracy: 0.8837 Epoch 29/70 128/6993 [..............................] - ETA: 0s - loss: 0.0095 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0117 - accuracy: 0.9996 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0159 - accuracy: 0.9976 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0149 - accuracy: 0.9977 - val_loss: 0.4431 - val_accuracy: 0.8847 Epoch 30/70 128/6993 [..............................] - ETA: 0s - loss: 0.0138 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0109 - accuracy: 0.9992 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0109 - accuracy: 0.9989 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0116 - accuracy: 0.9986 - val_loss: 0.4385 - val_accuracy: 0.8868 Epoch 31/70 128/6993 [..............................] - ETA: 0s - loss: 0.0046 - accuracy: 1.0000 3072/6993 [============>.................] - ETA: 0s - loss: 0.0212 - accuracy: 0.9964 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0154 - accuracy: 0.9979 6993/6993 [==============================] - 0s 22us/sample - loss: 0.0155 - accuracy: 0.9979 - val_loss: 0.4559 - val_accuracy: 0.8782 Epoch 32/70 128/6993 [..............................] - ETA: 0s - loss: 0.0294 - accuracy: 0.9922 3200/6993 [============>.................] - ETA: 0s - loss: 0.0125 - accuracy: 0.9972 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0166 - accuracy: 0.9964 6993/6993 [==============================] - 0s 25us/sample - loss: 0.0166 - accuracy: 0.9964 - val_loss: 0.4961 - val_accuracy: 0.8721 Epoch 33/70 128/6993 [..............................] - ETA: 0s - loss: 0.0334 - accuracy: 0.9844 3072/6993 [============>.................] - ETA: 0s - loss: 0.0190 - accuracy: 0.9958 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0150 - accuracy: 0.9972 6912/6993 [============================>.] - ETA: 0s - loss: 0.0138 - accuracy: 0.9977 6993/6993 [==============================] - 0s 32us/sample - loss: 0.0142 - accuracy: 0.9976 - val_loss: 0.4458 - val_accuracy: 0.8857 Epoch 34/70 128/6993 [..............................] - ETA: 0s - loss: 0.0051 - accuracy: 1.0000 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0114 - accuracy: 0.9980 4096/6993 [================>.............] - ETA: 0s - loss: 0.0110 - accuracy: 0.9973 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0108 - accuracy: 0.9974 6993/6993 [==============================] - 0s 31us/sample - loss: 0.0110 - accuracy: 0.9974 - val_loss: 0.4579 - val_accuracy: 0.8837 Epoch 35/70 128/6993 [..............................] - ETA: 0s - loss: 0.0091 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0082 - accuracy: 0.9992 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0092 - accuracy: 0.9985 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0151 - accuracy: 0.9970 6993/6993 [==============================] - 0s 30us/sample - loss: 0.0167 - accuracy: 0.9966 - val_loss: 0.5564 - val_accuracy: 0.8771 Epoch 36/70 128/6993 [..............................] - ETA: 0s - loss: 0.0984 - accuracy: 0.9844 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1142 - accuracy: 0.9743 4352/6993 [=================>............] - ETA: 0s - loss: 0.1451 - accuracy: 0.9607 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1331 - accuracy: 0.9622 6993/6993 [==============================] - 0s 30us/sample - loss: 0.1333 - accuracy: 0.9607 - val_loss: 0.5454 - val_accuracy: 0.8635 Epoch 37/70 128/6993 [..............................] - ETA: 0s - loss: 0.0363 - accuracy: 0.9922 3200/6993 [============>.................] - ETA: 0s - loss: 0.0856 - accuracy: 0.9772 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0806 - accuracy: 0.9784 6993/6993 [==============================] - 0s 23us/sample - loss: 0.0805 - accuracy: 0.9784 - val_loss: 0.6043 - val_accuracy: 0.8615 Epoch 38/70 128/6993 [..............................] - ETA: 0s - loss: 0.0843 - accuracy: 0.9766 3328/6993 [=============>................] - ETA: 0s - loss: 0.0481 - accuracy: 0.9889 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0391 - accuracy: 0.9911 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0378 - accuracy: 0.9914 - val_loss: 0.4777 - val_accuracy: 0.8782 Epoch 39/70 128/6993 [..............................] - ETA: 0s - loss: 0.0211 - accuracy: 1.0000 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0222 - accuracy: 0.9945 4096/6993 [================>.............] - ETA: 0s - loss: 0.0212 - accuracy: 0.9958 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0180 - accuracy: 0.9967 6993/6993 [==============================] - 0s 31us/sample - loss: 0.0174 - accuracy: 0.9967 - val_loss: 0.4560 - val_accuracy: 0.8847 Epoch 40/70 128/6993 [..............................] - ETA: 0s - loss: 0.0063 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0113 - accuracy: 0.9979 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0087 - accuracy: 0.9990 6993/6993 [==============================] - 0s 30us/sample - loss: 0.0086 - accuracy: 0.9990 - val_loss: 0.4476 - val_accuracy: 0.8918 Epoch 41/70 128/6993 [..............................] - ETA: 0s - loss: 0.0205 - accuracy: 0.9922 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0103 - accuracy: 0.9977 4352/6993 [=================>............] - ETA: 0s - loss: 0.0077 - accuracy: 0.9986 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0078 - accuracy: 0.9985 6993/6993 [==============================] - 0s 31us/sample - loss: 0.0076 - accuracy: 0.9986 - val_loss: 0.4580 - val_accuracy: 0.8893 Epoch 42/70 128/6993 [..............................] - ETA: 0s - loss: 0.0151 - accuracy: 0.9922 3200/6993 [============>.................] - ETA: 0s - loss: 0.0060 - accuracy: 0.9987 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0052 - accuracy: 0.9993 6993/6993 [==============================] - 0s 30us/sample - loss: 0.0051 - accuracy: 0.9993 - val_loss: 0.4552 - val_accuracy: 0.8928 Epoch 43/70 128/6993 [..............................] - ETA: 0s - loss: 0.0035 - accuracy: 1.0000 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0032 - accuracy: 1.0000 4224/6993 [=================>............] - ETA: 0s - loss: 0.0041 - accuracy: 0.9995 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0055 - accuracy: 0.9991 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0054 - accuracy: 0.9991 - val_loss: 0.4621 - val_accuracy: 0.8933 Epoch 44/70 128/6993 [..............................] - ETA: 0s - loss: 0.0183 - accuracy: 0.9922 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0061 - accuracy: 0.9988 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0058 - accuracy: 0.9989 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0061 - accuracy: 0.9986 - val_loss: 0.4794 - val_accuracy: 0.8883 Epoch 45/70 128/6993 [..............................] - ETA: 0s - loss: 0.0037 - accuracy: 1.0000 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0047 - accuracy: 0.9991 4224/6993 [=================>............] - ETA: 0s - loss: 0.0077 - accuracy: 0.9983 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0139 - accuracy: 0.9963 6993/6993 [==============================] - 0s 33us/sample - loss: 0.0132 - accuracy: 0.9966 - val_loss: 0.4898 - val_accuracy: 0.8893 Epoch 46/70 128/6993 [..............................] - ETA: 0s - loss: 0.0049 - accuracy: 1.0000 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0073 - accuracy: 0.9985 3968/6993 [================>.............] - ETA: 0s - loss: 0.0073 - accuracy: 0.9987 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0070 - accuracy: 0.9985 6993/6993 [==============================] - 0s 33us/sample - loss: 0.0075 - accuracy: 0.9983 - val_loss: 0.4631 - val_accuracy: 0.8908 Epoch 47/70 128/6993 [..............................] - ETA: 0s - loss: 0.0017 - accuracy: 1.0000 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0057 - accuracy: 0.9987 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0053 - accuracy: 0.9990 6993/6993 [==============================] - 0s 26us/sample - loss: 0.0063 - accuracy: 0.9987 - val_loss: 0.4691 - val_accuracy: 0.8948 Epoch 48/70 128/6993 [..............................] - ETA: 0s - loss: 0.0019 - accuracy: 1.0000 3072/6993 [============>.................] - ETA: 0s - loss: 0.0045 - accuracy: 0.9987 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0053 - accuracy: 0.9984 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0048 - accuracy: 0.9987 - val_loss: 0.4728 - val_accuracy: 0.8918 Epoch 49/70 128/6993 [..............................] - ETA: 0s - loss: 0.0023 - accuracy: 1.0000 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0024 - accuracy: 0.9995 4224/6993 [=================>............] - ETA: 0s - loss: 0.0032 - accuracy: 0.9993 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0057 - accuracy: 0.9989 6993/6993 [==============================] - 0s 31us/sample - loss: 0.0058 - accuracy: 0.9989 - val_loss: 0.5002 - val_accuracy: 0.8878 Epoch 50/70 128/6993 [..............................] - ETA: 0s - loss: 0.0245 - accuracy: 0.9922 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0088 - accuracy: 0.9985 4096/6993 [================>.............] - ETA: 0s - loss: 0.0072 - accuracy: 0.9985 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0083 - accuracy: 0.9979 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0080 - accuracy: 0.9980 - val_loss: 0.4955 - val_accuracy: 0.8883 Epoch 51/70 128/6993 [..............................] - ETA: 0s - loss: 0.0026 - accuracy: 1.0000 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0064 - accuracy: 0.9982 4352/6993 [=================>............] - ETA: 0s - loss: 0.0053 - accuracy: 0.9984 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0056 - accuracy: 0.9984 6993/6993 [==============================] - 0s 32us/sample - loss: 0.0060 - accuracy: 0.9984 - val_loss: 0.4888 - val_accuracy: 0.8913 Epoch 52/70 128/6993 [..............................] - ETA: 0s - loss: 0.0023 - accuracy: 1.0000 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0035 - accuracy: 0.9995 4224/6993 [=================>............] - ETA: 0s - loss: 0.0060 - accuracy: 0.9986 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0060 - accuracy: 0.9987 6993/6993 [==============================] - 0s 33us/sample - loss: 0.0059 - accuracy: 0.9987 - val_loss: 0.4792 - val_accuracy: 0.8938 Epoch 53/70 128/6993 [..............................] - ETA: 0s - loss: 0.0018 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0037 - accuracy: 0.9993 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0035 - accuracy: 0.9993 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0037 - accuracy: 0.9991 - val_loss: 0.4795 - val_accuracy: 0.8964 Epoch 54/70 128/6993 [..............................] - ETA: 0s - loss: 0.0019 - accuracy: 1.0000 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0034 - accuracy: 0.9995 4096/6993 [================>.............] - ETA: 0s - loss: 0.0033 - accuracy: 0.9995 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0034 - accuracy: 0.9993 6993/6993 [==============================] - 0s 32us/sample - loss: 0.0033 - accuracy: 0.9994 - val_loss: 0.4844 - val_accuracy: 0.8953 Epoch 55/70 128/6993 [..............................] - ETA: 0s - loss: 0.0013 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0036 - accuracy: 0.9989 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0030 - accuracy: 0.9992 6993/6993 [==============================] - 0s 25us/sample - loss: 0.0032 - accuracy: 0.9991 - val_loss: 0.4970 - val_accuracy: 0.8938 Epoch 56/70 128/6993 [..............................] - ETA: 0s - loss: 0.0013 - accuracy: 1.0000 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0047 - accuracy: 0.9991 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0065 - accuracy: 0.9986 6993/6993 [==============================] - 0s 22us/sample - loss: 0.0051 - accuracy: 0.9990 - val_loss: 0.4912 - val_accuracy: 0.8918 Epoch 57/70 128/6993 [..............................] - ETA: 0s - loss: 0.0307 - accuracy: 0.9922 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0070 - accuracy: 0.9979 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0066 - accuracy: 0.9984 6993/6993 [==============================] - 0s 30us/sample - loss: 0.0065 - accuracy: 0.9986 - val_loss: 0.4974 - val_accuracy: 0.8918 Epoch 58/70 128/6993 [..............................] - ETA: 0s - loss: 0.0045 - accuracy: 1.0000 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0083 - accuracy: 0.9982 4224/6993 [=================>............] - ETA: 0s - loss: 0.0102 - accuracy: 0.9979 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0094 - accuracy: 0.9981 6993/6993 [==============================] - 0s 31us/sample - loss: 0.0098 - accuracy: 0.9980 - val_loss: 0.5630 - val_accuracy: 0.8792 Epoch 59/70 128/6993 [..............................] - ETA: 0s - loss: 0.0040 - accuracy: 1.0000 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0063 - accuracy: 0.9987 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0129 - accuracy: 0.9972 6993/6993 [==============================] - 0s 26us/sample - loss: 0.0192 - accuracy: 0.9944 - val_loss: 0.6083 - val_accuracy: 0.8782 Epoch 60/70 128/6993 [..............................] - ETA: 0s - loss: 0.0165 - accuracy: 0.9922 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0343 - accuracy: 0.9903 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0408 - accuracy: 0.9853 6993/6993 [==============================] - 0s 22us/sample - loss: 0.0469 - accuracy: 0.9830 - val_loss: 0.6008 - val_accuracy: 0.8751 Epoch 61/70 128/6993 [..............................] - ETA: 0s - loss: 0.0251 - accuracy: 0.9922 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0875 - accuracy: 0.9715 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0877 - accuracy: 0.9709 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0906 - accuracy: 0.9701 - val_loss: 0.6082 - val_accuracy: 0.8579 Epoch 62/70 128/6993 [..............................] - ETA: 0s - loss: 0.0490 - accuracy: 0.9922 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0646 - accuracy: 0.9766 4352/6993 [=================>............] - ETA: 0s - loss: 0.0538 - accuracy: 0.9800 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0527 - accuracy: 0.9822 6993/6993 [==============================] - 0s 30us/sample - loss: 0.0514 - accuracy: 0.9827 - val_loss: 0.5210 - val_accuracy: 0.8792 Epoch 63/70 128/6993 [..............................] - ETA: 0s - loss: 0.0223 - accuracy: 0.9922 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0340 - accuracy: 0.9887 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0319 - accuracy: 0.9891 6993/6993 [==============================] - 0s 25us/sample - loss: 0.0326 - accuracy: 0.9898 - val_loss: 0.5771 - val_accuracy: 0.8807 Epoch 64/70 128/6993 [..............................] - ETA: 0s - loss: 0.0560 - accuracy: 0.9688 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0286 - accuracy: 0.9895 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0258 - accuracy: 0.9915 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0226 - accuracy: 0.9922 6993/6993 [==============================] - 0s 33us/sample - loss: 0.0214 - accuracy: 0.9929 - val_loss: 0.4963 - val_accuracy: 0.8933 Epoch 65/70 128/6993 [..............................] - ETA: 0s - loss: 0.0106 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0088 - accuracy: 0.9979 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0062 - accuracy: 0.9988 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0066 - accuracy: 0.9987 - val_loss: 0.4816 - val_accuracy: 0.8948 Epoch 66/70 128/6993 [..............................] - ETA: 0s - loss: 0.0061 - accuracy: 1.0000 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0048 - accuracy: 0.9991 4224/6993 [=================>............] - ETA: 0s - loss: 0.0043 - accuracy: 0.9991 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0039 - accuracy: 0.9992 6993/6993 [==============================] - 0s 34us/sample - loss: 0.0040 - accuracy: 0.9991 - val_loss: 0.4886 - val_accuracy: 0.8918 Epoch 67/70 128/6993 [..............................] - ETA: 0s - loss: 0.0011 - accuracy: 1.0000 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0028 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0037 - accuracy: 0.9989 4096/6993 [================>.............] - ETA: 0s - loss: 0.0034 - accuracy: 0.9990 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0037 - accuracy: 0.9991 6912/6993 [============================>.] - ETA: 0s - loss: 0.0038 - accuracy: 0.9991 6993/6993 [==============================] - 0s 45us/sample - loss: 0.0038 - accuracy: 0.9991 - val_loss: 0.4661 - val_accuracy: 0.8999 Epoch 68/70 128/6993 [..............................] - ETA: 0s - loss: 0.0018 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0029 - accuracy: 0.9993 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0031 - accuracy: 0.9990 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0037 - accuracy: 0.9990 - val_loss: 0.4758 - val_accuracy: 0.8994 Epoch 69/70 128/6993 [..............................] - ETA: 0s - loss: 0.0020 - accuracy: 1.0000 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0023 - accuracy: 0.9993 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0031 - accuracy: 0.9991 6993/6993 [==============================] - 0s 25us/sample - loss: 0.0028 - accuracy: 0.9993 - val_loss: 0.4728 - val_accuracy: 0.9004 Epoch 70/70 128/6993 [..............................] - ETA: 0s - loss: 7.5332e-04 - accuracy: 1.0000 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0024 - accuracy: 0.9994 4096/6993 [================>.............] - ETA: 0s - loss: 0.0028 - accuracy: 0.9993 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0032 - accuracy: 0.9991 - val_loss: 0.4798 - val_accuracy: 0.8974 1019/1019 - 0s - loss: 0.5982 - accuracy: 0.8871 Test accuracy: 0.88714427
As we can see from above result, the accuracy reaches more than 90%, but I try to build another fcnn model which is more complicated and there will be dropout layer after each fully connected layer. Also I add the dimensionality in this model.
You can run the "python main.py FCNN2" in the terminal of Pycharm.(Warning: the right Virtual environment should be venv_python3.6) And you will get result as below shown.
Or you can directly run ! python main.py FCNN2 in the jupyter notebook
! python main.py FCNN2
Model: "sequential" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= dense (Dense) (None, 1024) 59392 _________________________________________________________________ dropout (Dropout) (None, 1024) 0 _________________________________________________________________ dense_1 (Dense) (None, 512) 524800 _________________________________________________________________ dropout_1 (Dropout) (None, 512) 0 _________________________________________________________________ dense_2 (Dense) (None, 256) 131328 _________________________________________________________________ dropout_2 (Dropout) (None, 256) 0 _________________________________________________________________ dense_3 (Dense) (None, 128) 32896 _________________________________________________________________ dropout_3 (Dropout) (None, 128) 0 _________________________________________________________________ dense_4 (Dense) (None, 64) 8256 _________________________________________________________________ dropout_4 (Dropout) (None, 64) 0 _________________________________________________________________ dense_5 (Dense) (None, 10) 650 =================================================================
2022-04-11 23:18:34.507205: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll 2022-04-11 23:18:39.556934: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 2022-04-11 23:18:39.561356: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll 2022-04-11 23:18:40.534244: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:18:40.534289: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:18:40.541936: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:18:41.216058: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:18:41.216078: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:18:41.216083: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:18:41.223585: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) WARNING:tensorflow:From D:\Programs\Anaconda_app\envs\comp47650_env\lib\site-packages\tensorflow_core\python\ops\resource_variable_ops.py:1630: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version. Instructions for updating: If using Keras pass *_constraint arguments to layers. 2022-04-11 23:18:41.296315: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:18:41.296356: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:18:41.301747: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:18:42.730555: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll 2022-04-11 23:23:35.367928: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:23:35.367955: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:23:35.375171: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
Total params: 757,322 Trainable params: 757,322 Non-trainable params: 0 _________________________________________________________________ Train on 6993 samples, validate on 1978 samples Epoch 1/500 128/6993 [..............................] - ETA: 26s - loss: 2.2910 - accuracy: 0.1406 1024/6993 [===>..........................] - ETA: 3s - loss: 2.1584 - accuracy: 0.2256 1920/6993 [=======>......................] - ETA: 1s - loss: 2.0323 - accuracy: 0.2714 2816/6993 [===========>..................] - ETA: 1s - loss: 1.9441 - accuracy: 0.3036 3840/6993 [===============>..............] - ETA: 0s - loss: 1.8687 - accuracy: 0.3320 4736/6993 [===================>..........] - ETA: 0s - loss: 1.7961 - accuracy: 0.3581 5632/6993 [=======================>......] - ETA: 0s - loss: 1.7470 - accuracy: 0.3759 6528/6993 [===========================>..] - ETA: 0s - loss: 1.7113 - accuracy: 0.3874 6993/6993 [==============================] - 1s 160us/sample - loss: 1.6905 - accuracy: 0.3955 - val_loss: 1.1817 - val_accuracy: 0.5905 Epoch 2/500 128/6993 [..............................] - ETA: 0s - loss: 1.3995 - accuracy: 0.4766 896/6993 [==>...........................] - ETA: 0s - loss: 1.3398 - accuracy: 0.5123 1792/6993 [======>.......................] - ETA: 0s - loss: 1.3337 - accuracy: 0.5212 2688/6993 [==========>...................] - ETA: 0s - loss: 1.3300 - accuracy: 0.5339 3584/6993 [==============>...............] - ETA: 0s - loss: 1.3094 - accuracy: 0.5416 4480/6993 [==================>...........] - ETA: 0s - loss: 1.2959 - accuracy: 0.5440 5376/6993 [======================>.......] - ETA: 0s - loss: 1.2812 - accuracy: 0.5519 6272/6993 [=========================>....] - ETA: 0s - loss: 1.2564 - accuracy: 0.5636 6993/6993 [==============================] - 1s 76us/sample - loss: 1.2492 - accuracy: 0.5671 - val_loss: 0.9574 - val_accuracy: 0.6775 Epoch 3/500 128/6993 [..............................] - ETA: 0s - loss: 1.0776 - accuracy: 0.6484 896/6993 [==>...........................] - ETA: 0s - loss: 1.0730 - accuracy: 0.6295 1792/6993 [======>.......................] - ETA: 0s - loss: 1.0526 - accuracy: 0.6367 2688/6993 [==========>...................] - ETA: 0s - loss: 1.0754 - accuracy: 0.6347 3584/6993 [==============>...............] - ETA: 0s - loss: 1.0540 - accuracy: 0.6448 4480/6993 [==================>...........] - ETA: 0s - loss: 1.0581 - accuracy: 0.6480 5376/6993 [======================>.......] - ETA: 0s - loss: 1.0563 - accuracy: 0.6512 6272/6993 [=========================>....] - ETA: 0s - loss: 1.0388 - accuracy: 0.6588 6993/6993 [==============================] - 1s 74us/sample - loss: 1.0309 - accuracy: 0.6602 - val_loss: 0.8278 - val_accuracy: 0.7235 Epoch 4/500 128/6993 [..............................] - ETA: 0s - loss: 1.0135 - accuracy: 0.6953 896/6993 [==>...........................] - ETA: 0s - loss: 0.9631 - accuracy: 0.6830 1792/6993 [======>.......................] - ETA: 0s - loss: 0.9355 - accuracy: 0.6970 2688/6993 [==========>...................] - ETA: 0s - loss: 0.9192 - accuracy: 0.6998 3584/6993 [==============>...............] - ETA: 0s - loss: 0.9096 - accuracy: 0.7023 4480/6993 [==================>...........] - ETA: 0s - loss: 0.9054 - accuracy: 0.7051 5376/6993 [======================>.......] - ETA: 0s - loss: 0.8996 - accuracy: 0.7070 6272/6993 [=========================>....] - ETA: 0s - loss: 0.9002 - accuracy: 0.7062 6993/6993 [==============================] - 1s 78us/sample - loss: 0.9010 - accuracy: 0.7046 - val_loss: 0.7394 - val_accuracy: 0.7568 Epoch 5/500 128/6993 [..............................] - ETA: 0s - loss: 0.6777 - accuracy: 0.7656 896/6993 [==>...........................] - ETA: 0s - loss: 0.7598 - accuracy: 0.7333 1792/6993 [======>.......................] - ETA: 0s - loss: 0.8156 - accuracy: 0.7288 2688/6993 [==========>...................] - ETA: 0s - loss: 0.8055 - accuracy: 0.7362 3584/6993 [==============>...............] - ETA: 0s - loss: 0.8077 - accuracy: 0.7386 4480/6993 [==================>...........] - ETA: 0s - loss: 0.8077 - accuracy: 0.7337 5376/6993 [======================>.......] - ETA: 0s - loss: 0.8000 - accuracy: 0.7381 6144/6993 [=========================>....] - ETA: 0s - loss: 0.7995 - accuracy: 0.7404 6993/6993 [==============================] - 1s 76us/sample - loss: 0.7974 - accuracy: 0.7407 - val_loss: 0.7494 - val_accuracy: 0.7513 Epoch 6/500 128/6993 [..............................] - ETA: 0s - loss: 0.7004 - accuracy: 0.7578 896/6993 [==>...........................] - ETA: 0s - loss: 0.6624 - accuracy: 0.7734 1792/6993 [======>.......................] - ETA: 0s - loss: 0.7062 - accuracy: 0.7723 2688/6993 [==========>...................] - ETA: 0s - loss: 0.7224 - accuracy: 0.7705 3584/6993 [==============>...............] - ETA: 0s - loss: 0.7176 - accuracy: 0.7698 4608/6993 [==================>...........] - ETA: 0s - loss: 0.7147 - accuracy: 0.7719 5632/6993 [=======================>......] - ETA: 0s - loss: 0.7057 - accuracy: 0.7736 6528/6993 [===========================>..] - ETA: 0s - loss: 0.7066 - accuracy: 0.7748 6993/6993 [==============================] - 0s 71us/sample - loss: 0.7039 - accuracy: 0.7758 - val_loss: 0.6024 - val_accuracy: 0.8043 Epoch 7/500 128/6993 [..............................] - ETA: 0s - loss: 0.5432 - accuracy: 0.8516 896/6993 [==>...........................] - ETA: 0s - loss: 0.5943 - accuracy: 0.8114 1920/6993 [=======>......................] - ETA: 0s - loss: 0.6112 - accuracy: 0.8016 2816/6993 [===========>..................] - ETA: 0s - loss: 0.6377 - accuracy: 0.7965 3584/6993 [==============>...............] - ETA: 0s - loss: 0.6415 - accuracy: 0.7946
2022-04-11 23:23:35.375269: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:23:35.375281: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:23:35.375287: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:23:35.381930: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) 2022-04-11 23:23:36.897565: W tensorflow/python/util/util.cc:299] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them.
4352/6993 [=================>............] - ETA: 0s - loss: 0.6256 - accuracy: 0.8006 4992/6993 [====================>.........] - ETA: 0s - loss: 0.6340 - accuracy: 0.7987 5760/6993 [=======================>......] - ETA: 0s - loss: 0.6321 - accuracy: 0.8003 6656/6993 [===========================>..] - ETA: 0s - loss: 0.6269 - accuracy: 0.8000 6993/6993 [==============================] - 1s 80us/sample - loss: 0.6286 - accuracy: 0.8004 - val_loss: 0.6136 - val_accuracy: 0.8109 Epoch 8/500 128/6993 [..............................] - ETA: 0s - loss: 0.5559 - accuracy: 0.8359 1024/6993 [===>..........................] - ETA: 0s - loss: 0.6031 - accuracy: 0.8066 1920/6993 [=======>......................] - ETA: 0s - loss: 0.5299 - accuracy: 0.8302 2688/6993 [==========>...................] - ETA: 0s - loss: 0.5229 - accuracy: 0.8311 3584/6993 [==============>...............] - ETA: 0s - loss: 0.5205 - accuracy: 0.8329 4480/6993 [==================>...........] - ETA: 0s - loss: 0.5404 - accuracy: 0.8277 5248/6993 [=====================>........] - ETA: 0s - loss: 0.5454 - accuracy: 0.8276 6144/6993 [=========================>....] - ETA: 0s - loss: 0.5562 - accuracy: 0.8244 6912/6993 [============================>.] - ETA: 0s - loss: 0.5611 - accuracy: 0.8228 6993/6993 [==============================] - 1s 78us/sample - loss: 0.5601 - accuracy: 0.8235 - val_loss: 0.5208 - val_accuracy: 0.8372 Epoch 9/500 128/6993 [..............................] - ETA: 0s - loss: 0.6158 - accuracy: 0.8047 896/6993 [==>...........................] - ETA: 0s - loss: 0.4889 - accuracy: 0.8337 1536/6993 [=====>........................] - ETA: 0s - loss: 0.4805 - accuracy: 0.8366 2304/6993 [========>.....................] - ETA: 0s - loss: 0.5018 - accuracy: 0.8329 3072/6993 [============>.................] - ETA: 0s - loss: 0.5039 - accuracy: 0.8333 3712/6993 [==============>...............] - ETA: 0s - loss: 0.5075 - accuracy: 0.8367 4480/6993 [==================>...........] - ETA: 0s - loss: 0.5036 - accuracy: 0.8391 5248/6993 [=====================>........] - ETA: 0s - loss: 0.5054 - accuracy: 0.8386 5888/6993 [========================>.....] - ETA: 0s - loss: 0.5044 - accuracy: 0.8410 6528/6993 [===========================>..] - ETA: 0s - loss: 0.5015 - accuracy: 0.8418 6993/6993 [==============================] - 1s 89us/sample - loss: 0.5077 - accuracy: 0.8408 - val_loss: 0.4910 - val_accuracy: 0.8448 Epoch 10/500 128/6993 [..............................] - ETA: 0s - loss: 0.4344 - accuracy: 0.8750 768/6993 [==>...........................] - ETA: 0s - loss: 0.4580 - accuracy: 0.8516 1536/6993 [=====>........................] - ETA: 0s - loss: 0.4414 - accuracy: 0.8600 2432/6993 [=========>....................] - ETA: 0s - loss: 0.4583 - accuracy: 0.8532 3200/6993 [============>.................] - ETA: 0s - loss: 0.4876 - accuracy: 0.8478 3840/6993 [===============>..............] - ETA: 0s - loss: 0.4939 - accuracy: 0.8461 4480/6993 [==================>...........] - ETA: 0s - loss: 0.4942 - accuracy: 0.8458 5120/6993 [====================>.........] - ETA: 0s - loss: 0.4961 - accuracy: 0.8449 5888/6993 [========================>.....] - ETA: 0s - loss: 0.4858 - accuracy: 0.8478 6656/6993 [===========================>..] - ETA: 0s - loss: 0.4851 - accuracy: 0.8477 6993/6993 [==============================] - 1s 84us/sample - loss: 0.4825 - accuracy: 0.8488 - val_loss: 0.5151 - val_accuracy: 0.8433 Epoch 11/500 128/6993 [..............................] - ETA: 0s - loss: 0.5182 - accuracy: 0.8203 896/6993 [==>...........................] - ETA: 0s - loss: 0.4054 - accuracy: 0.8650 1792/6993 [======>.......................] - ETA: 0s - loss: 0.4081 - accuracy: 0.8627 2688/6993 [==========>...................] - ETA: 0s - loss: 0.4100 - accuracy: 0.8664 3328/6993 [=============>................] - ETA: 0s - loss: 0.4254 - accuracy: 0.8612 3968/6993 [================>.............] - ETA: 0s - loss: 0.4366 - accuracy: 0.8604 4736/6993 [===================>..........] - ETA: 0s - loss: 0.4316 - accuracy: 0.8632 5504/6993 [======================>.......] - ETA: 0s - loss: 0.4288 - accuracy: 0.8636 6144/6993 [=========================>....] - ETA: 0s - loss: 0.4389 - accuracy: 0.8620 6784/6993 [============================>.] - ETA: 0s - loss: 0.4431 - accuracy: 0.8629 6993/6993 [==============================] - 1s 82us/sample - loss: 0.4452 - accuracy: 0.8623 - val_loss: 0.4728 - val_accuracy: 0.8473 Epoch 12/500 128/6993 [..............................] - ETA: 0s - loss: 0.3876 - accuracy: 0.8984 1024/6993 [===>..........................] - ETA: 0s - loss: 0.3593 - accuracy: 0.8896 1920/6993 [=======>......................] - ETA: 0s - loss: 0.3815 - accuracy: 0.8813 2688/6993 [==========>...................] - ETA: 0s - loss: 0.3778 - accuracy: 0.8813 3584/6993 [==============>...............] - ETA: 0s - loss: 0.3759 - accuracy: 0.8834 4224/6993 [=================>............] - ETA: 0s - loss: 0.3724 - accuracy: 0.8819 5248/6993 [=====================>........] - ETA: 0s - loss: 0.3826 - accuracy: 0.8784 6144/6993 [=========================>....] - ETA: 0s - loss: 0.3836 - accuracy: 0.8771 6912/6993 [============================>.] - ETA: 0s - loss: 0.3872 - accuracy: 0.8776 6993/6993 [==============================] - 1s 77us/sample - loss: 0.3866 - accuracy: 0.8779 - val_loss: 0.4821 - val_accuracy: 0.8554 Epoch 13/500 128/6993 [..............................] - ETA: 0s - loss: 0.5334 - accuracy: 0.8516 896/6993 [==>...........................] - ETA: 0s - loss: 0.3419 - accuracy: 0.9040 1664/6993 [======>.......................] - ETA: 0s - loss: 0.3512 - accuracy: 0.8936 2432/6993 [=========>....................] - ETA: 0s - loss: 0.3487 - accuracy: 0.8972 3200/6993 [============>.................] - ETA: 0s - loss: 0.3846 - accuracy: 0.8888 3968/6993 [================>.............] - ETA: 0s - loss: 0.3808 - accuracy: 0.8863 4736/6993 [===================>..........] - ETA: 0s - loss: 0.3902 - accuracy: 0.8828 5504/6993 [======================>.......] - ETA: 0s - loss: 0.3903 - accuracy: 0.8832 6400/6993 [==========================>...] - ETA: 0s - loss: 0.3846 - accuracy: 0.8847 6993/6993 [==============================] - 1s 74us/sample - loss: 0.3786 - accuracy: 0.8867 - val_loss: 0.4336 - val_accuracy: 0.8792 Epoch 14/500 128/6993 [..............................] - ETA: 0s - loss: 0.2625 - accuracy: 0.9219 1024/6993 [===>..........................] - ETA: 0s - loss: 0.3139 - accuracy: 0.9033 1920/6993 [=======>......................] - ETA: 0s - loss: 0.3294 - accuracy: 0.8979 2688/6993 [==========>...................] - ETA: 0s - loss: 0.3184 - accuracy: 0.9044 3456/6993 [=============>................] - ETA: 0s - loss: 0.3178 - accuracy: 0.9034 4224/6993 [=================>............] - ETA: 0s - loss: 0.3232 - accuracy: 0.9013 4992/6993 [====================>.........] - ETA: 0s - loss: 0.3251 - accuracy: 0.8998 5760/6993 [=======================>......] - ETA: 0s - loss: 0.3367 - accuracy: 0.8981 6528/6993 [===========================>..] - ETA: 0s - loss: 0.3447 - accuracy: 0.8974 6993/6993 [==============================] - 1s 76us/sample - loss: 0.3421 - accuracy: 0.8979 - val_loss: 0.4408 - val_accuracy: 0.8716 Epoch 15/500 128/6993 [..............................] - ETA: 0s - loss: 0.2575 - accuracy: 0.9141 1152/6993 [===>..........................] - ETA: 0s - loss: 0.2778 - accuracy: 0.9115 2048/6993 [=======>......................] - ETA: 0s - loss: 0.2950 - accuracy: 0.9087 2944/6993 [===========>..................] - ETA: 0s - loss: 0.3132 - accuracy: 0.9022 3840/6993 [===============>..............] - ETA: 0s - loss: 0.3104 - accuracy: 0.9039 4736/6993 [===================>..........] - ETA: 0s - loss: 0.3193 - accuracy: 0.9012 5376/6993 [======================>.......] - ETA: 0s - loss: 0.3184 - accuracy: 0.9016 6144/6993 [=========================>....] - ETA: 0s - loss: 0.3097 - accuracy: 0.9032 6912/6993 [============================>.] - ETA: 0s - loss: 0.3167 - accuracy: 0.9003 6993/6993 [==============================] - 1s 76us/sample - loss: 0.3162 - accuracy: 0.9006 - val_loss: 0.4242 - val_accuracy: 0.8751 Epoch 16/500 128/6993 [..............................] - ETA: 0s - loss: 0.2454 - accuracy: 0.9062 1152/6993 [===>..........................] - ETA: 0s - loss: 0.3076 - accuracy: 0.9123 2176/6993 [========>.....................] - ETA: 0s - loss: 0.3065 - accuracy: 0.9108 3200/6993 [============>.................] - ETA: 0s - loss: 0.3066 - accuracy: 0.9094 4224/6993 [=================>............] - ETA: 0s - loss: 0.2953 - accuracy: 0.9115 5248/6993 [=====================>........] - ETA: 0s - loss: 0.2874 - accuracy: 0.9131 6272/6993 [=========================>....] - ETA: 0s - loss: 0.2956 - accuracy: 0.9110 6993/6993 [==============================] - 0s 66us/sample - loss: 0.2956 - accuracy: 0.9112 - val_loss: 0.4735 - val_accuracy: 0.8665 Epoch 17/500 128/6993 [..............................] - ETA: 0s - loss: 0.3224 - accuracy: 0.9062 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2850 - accuracy: 0.9209 2048/6993 [=======>......................] - ETA: 0s - loss: 0.2720 - accuracy: 0.9233 2944/6993 [===========>..................] - ETA: 0s - loss: 0.2542 - accuracy: 0.9249 3968/6993 [================>.............] - ETA: 0s - loss: 0.2686 - accuracy: 0.9234 4864/6993 [===================>..........] - ETA: 0s - loss: 0.2678 - accuracy: 0.9217 5632/6993 [=======================>......] - ETA: 0s - loss: 0.2709 - accuracy: 0.9206 6400/6993 [==========================>...] - ETA: 0s - loss: 0.2733 - accuracy: 0.9186 6993/6993 [==============================] - 1s 74us/sample - loss: 0.2708 - accuracy: 0.9186 - val_loss: 0.4346 - val_accuracy: 0.8822 Epoch 18/500 128/6993 [..............................] - ETA: 0s - loss: 0.2224 - accuracy: 0.9453 896/6993 [==>...........................] - ETA: 0s - loss: 0.2286 - accuracy: 0.9241 1792/6993 [======>.......................] - ETA: 0s - loss: 0.2426 - accuracy: 0.9241 2816/6993 [===========>..................] - ETA: 0s - loss: 0.2425 - accuracy: 0.9265 3712/6993 [==============>...............] - ETA: 0s - loss: 0.2372 - accuracy: 0.9278 4736/6993 [===================>..........] - ETA: 0s - loss: 0.2432 - accuracy: 0.9267 5632/6993 [=======================>......] - ETA: 0s - loss: 0.2418 - accuracy: 0.9276 6656/6993 [===========================>..] - ETA: 0s - loss: 0.2487 - accuracy: 0.9271 6993/6993 [==============================] - 0s 71us/sample - loss: 0.2538 - accuracy: 0.9264 - val_loss: 0.4114 - val_accuracy: 0.8893 Epoch 19/500 128/6993 [..............................] - ETA: 0s - loss: 0.2957 - accuracy: 0.9062 896/6993 [==>...........................] - ETA: 0s - loss: 0.2516 - accuracy: 0.9219 1664/6993 [======>.......................] - ETA: 0s - loss: 0.2435 - accuracy: 0.9285 2432/6993 [=========>....................] - ETA: 0s - loss: 0.2442 - accuracy: 0.9243 3200/6993 [============>.................] - ETA: 0s - loss: 0.2513 - accuracy: 0.9216 3968/6993 [================>.............] - ETA: 0s - loss: 0.2430 - accuracy: 0.9224 4992/6993 [====================>.........] - ETA: 0s - loss: 0.2339 - accuracy: 0.9261 5760/6993 [=======================>......] - ETA: 0s - loss: 0.2334 - accuracy: 0.9269 6528/6993 [===========================>..] - ETA: 0s - loss: 0.2322 - accuracy: 0.9280 6993/6993 [==============================] - 1s 79us/sample - loss: 0.2329 - accuracy: 0.9279 - val_loss: 0.3994 - val_accuracy: 0.8868 Epoch 20/500 128/6993 [..............................] - ETA: 0s - loss: 0.2382 - accuracy: 0.9219 896/6993 [==>...........................] - ETA: 0s - loss: 0.2262 - accuracy: 0.9286 1664/6993 [======>.......................] - ETA: 0s - loss: 0.2393 - accuracy: 0.9285 2432/6993 [=========>....................] - ETA: 0s - loss: 0.2364 - accuracy: 0.9313 3072/6993 [============>.................] - ETA: 0s - loss: 0.2275 - accuracy: 0.9316 3712/6993 [==============>...............] - ETA: 0s - loss: 0.2212 - accuracy: 0.9327 4352/6993 [=================>............] - ETA: 0s - loss: 0.2302 - accuracy: 0.9308 4992/6993 [====================>.........] - ETA: 0s - loss: 0.2283 - accuracy: 0.9317 5760/6993 [=======================>......] - ETA: 0s - loss: 0.2234 - accuracy: 0.9328 6528/6993 [===========================>..] - ETA: 0s - loss: 0.2285 - accuracy: 0.9306 6993/6993 [==============================] - 1s 85us/sample - loss: 0.2268 - accuracy: 0.9309 - val_loss: 0.4084 - val_accuracy: 0.8974 Epoch 21/500 128/6993 [..............................] - ETA: 0s - loss: 0.0772 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1472 - accuracy: 0.9557 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1944 - accuracy: 0.9414 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1849 - accuracy: 0.9436 3072/6993 [============>.................] - ETA: 0s - loss: 0.2076 - accuracy: 0.9365 3840/6993 [===============>..............] - ETA: 0s - loss: 0.2043 - accuracy: 0.9372 4608/6993 [==================>...........] - ETA: 0s - loss: 0.2036 - accuracy: 0.9395 5376/6993 [======================>.......] - ETA: 0s - loss: 0.2052 - accuracy: 0.9362 6272/6993 [=========================>....] - ETA: 0s - loss: 0.2065 - accuracy: 0.9354 6993/6993 [==============================] - 1s 80us/sample - loss: 0.2087 - accuracy: 0.9352 - val_loss: 0.4212 - val_accuracy: 0.8862 Epoch 22/500 128/6993 [..............................] - ETA: 0s - loss: 0.1550 - accuracy: 0.9375 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1809 - accuracy: 0.9492 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1937 - accuracy: 0.9443 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1884 - accuracy: 0.9457 3584/6993 [==============>...............] - ETA: 0s - loss: 0.2003 - accuracy: 0.9439 4480/6993 [==================>...........] - ETA: 0s - loss: 0.2243 - accuracy: 0.9413 5376/6993 [======================>.......] - ETA: 0s - loss: 0.2276 - accuracy: 0.9381 6272/6993 [=========================>....] - ETA: 0s - loss: 0.2274 - accuracy: 0.9375 6993/6993 [==============================] - 1s 78us/sample - loss: 0.2263 - accuracy: 0.9369 - val_loss: 0.3601 - val_accuracy: 0.8994 Epoch 23/500 128/6993 [..............................] - ETA: 0s - loss: 0.2359 - accuracy: 0.8984 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2235 - accuracy: 0.9287 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1989 - accuracy: 0.9391 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1930 - accuracy: 0.9394 3584/6993 [==============>...............] - ETA: 0s - loss: 0.2045 - accuracy: 0.9367 4480/6993 [==================>...........] - ETA: 0s - loss: 0.2087 - accuracy: 0.9368 5248/6993 [=====================>........] - ETA: 0s - loss: 0.2189 - accuracy: 0.9337 6144/6993 [=========================>....] - ETA: 0s - loss: 0.2226 - accuracy: 0.9320 6912/6993 [============================>.] - ETA: 0s - loss: 0.2211 - accuracy: 0.9329 6993/6993 [==============================] - 1s 80us/sample - loss: 0.2208 - accuracy: 0.9329 - val_loss: 0.3489 - val_accuracy: 0.9050 Epoch 24/500 128/6993 [..............................] - ETA: 0s - loss: 0.1346 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.1917 - accuracy: 0.9453 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1820 - accuracy: 0.9471 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1734 - accuracy: 0.9488 3328/6993 [=============>................] - ETA: 0s - loss: 0.1758 - accuracy: 0.9483 4224/6993 [=================>............] - ETA: 0s - loss: 0.1843 - accuracy: 0.9463 4992/6993 [====================>.........] - ETA: 0s - loss: 0.2025 - accuracy: 0.9447 5888/6993 [========================>.....] - ETA: 0s - loss: 0.2024 - accuracy: 0.9443 6656/6993 [===========================>..] - ETA: 0s - loss: 0.2014 - accuracy: 0.9435 6993/6993 [==============================] - 1s 80us/sample - loss: 0.2006 - accuracy: 0.9434 - val_loss: 0.3391 - val_accuracy: 0.9060 Epoch 25/500 128/6993 [..............................] - ETA: 0s - loss: 0.1518 - accuracy: 0.9609 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1739 - accuracy: 0.9502 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1810 - accuracy: 0.9526 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1756 - accuracy: 0.9516 3328/6993 [=============>................] - ETA: 0s - loss: 0.1838 - accuracy: 0.9492 3968/6993 [================>.............] - ETA: 0s - loss: 0.1775 - accuracy: 0.9509 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1860 - accuracy: 0.9496 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1852 - accuracy: 0.9487 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1825 - accuracy: 0.9504 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1808 - accuracy: 0.9504 - val_loss: 0.4013 - val_accuracy: 0.8994 Epoch 26/500 128/6993 [..............................] - ETA: 0s - loss: 0.2161 - accuracy: 0.9297 896/6993 [==>...........................] - ETA: 0s - loss: 0.1371 - accuracy: 0.9665 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1567 - accuracy: 0.9537 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1734 - accuracy: 0.9480 3456/6993 [=============>................] - ETA: 0s - loss: 0.1738 - accuracy: 0.9499 4352/6993 [=================>............] - ETA: 0s - loss: 0.1697 - accuracy: 0.9501 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1770 - accuracy: 0.9480 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1764 - accuracy: 0.9475 6912/6993 [============================>.] - ETA: 0s - loss: 0.1707 - accuracy: 0.9482 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1708 - accuracy: 0.9482 - val_loss: 0.4318 - val_accuracy: 0.9044 Epoch 27/500 128/6993 [..............................] - ETA: 0s - loss: 0.0679 - accuracy: 0.9609 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1383 - accuracy: 0.9561 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1622 - accuracy: 0.9547 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1607 - accuracy: 0.9557 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1700 - accuracy: 0.9520 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1659 - accuracy: 0.9533 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1637 - accuracy: 0.9552 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1722 - accuracy: 0.9544 6993/6993 [==============================] - 1s 73us/sample - loss: 0.1681 - accuracy: 0.9550 - val_loss: 0.3684 - val_accuracy: 0.9090 Epoch 28/500 128/6993 [..............................] - ETA: 0s - loss: 0.1414 - accuracy: 0.9453 1152/6993 [===>..........................] - ETA: 0s - loss: 0.1305 - accuracy: 0.9557 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1412 - accuracy: 0.9541 3072/6993 [============>.................] - ETA: 0s - loss: 0.1547 - accuracy: 0.9505 3968/6993 [================>.............] - ETA: 0s - loss: 0.1491 - accuracy: 0.9516 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1505 - accuracy: 0.9521 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1499 - accuracy: 0.9540 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1527 - accuracy: 0.9538 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1540 - accuracy: 0.9540 - val_loss: 0.3268 - val_accuracy: 0.9120 Epoch 29/500 128/6993 [..............................] - ETA: 0s - loss: 0.2342 - accuracy: 0.9297 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1315 - accuracy: 0.9580 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1438 - accuracy: 0.9585 3072/6993 [============>.................] - ETA: 0s - loss: 0.1535 - accuracy: 0.9564 4096/6993 [================>.............] - ETA: 0s - loss: 0.1632 - accuracy: 0.9546 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1663 - accuracy: 0.9533 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1665 - accuracy: 0.9526 6993/6993 [==============================] - 0s 69us/sample - loss: 0.1685 - accuracy: 0.9528 - val_loss: 0.3896 - val_accuracy: 0.9120 Epoch 30/500 128/6993 [..............................] - ETA: 0s - loss: 0.1549 - accuracy: 0.9531 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1148 - accuracy: 0.9600 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1323 - accuracy: 0.9599 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1454 - accuracy: 0.9555 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1550 - accuracy: 0.9544 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1535 - accuracy: 0.9548 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1526 - accuracy: 0.9556 6784/6993 [============================>.] - ETA: 0s - loss: 0.1495 - accuracy: 0.9562 6993/6993 [==============================] - 0s 69us/sample - loss: 0.1514 - accuracy: 0.9561 - val_loss: 0.4073 - val_accuracy: 0.9044 Epoch 31/500 128/6993 [..............................] - ETA: 0s - loss: 0.0428 - accuracy: 0.9922 1152/6993 [===>..........................] - ETA: 0s - loss: 0.1586 - accuracy: 0.9540 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1589 - accuracy: 0.9531 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1670 - accuracy: 0.9518 3968/6993 [================>.............] - ETA: 0s - loss: 0.1566 - accuracy: 0.9554 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1503 - accuracy: 0.9571 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1474 - accuracy: 0.9577 6912/6993 [============================>.] - ETA: 0s - loss: 0.1489 - accuracy: 0.9575 6993/6993 [==============================] - 1s 72us/sample - loss: 0.1476 - accuracy: 0.9578 - val_loss: 0.3929 - val_accuracy: 0.9065 Epoch 32/500 128/6993 [..............................] - ETA: 0s - loss: 0.1321 - accuracy: 0.9609 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1203 - accuracy: 0.9707 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1033 - accuracy: 0.9703 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1218 - accuracy: 0.9664 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1185 - accuracy: 0.9682 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1261 - accuracy: 0.9657 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1368 - accuracy: 0.9635 6784/6993 [============================>.] - ETA: 0s - loss: 0.1339 - accuracy: 0.9630 6993/6993 [==============================] - 0s 69us/sample - loss: 0.1336 - accuracy: 0.9627 - val_loss: 0.3824 - val_accuracy: 0.9130 Epoch 33/500 128/6993 [..............................] - ETA: 0s - loss: 0.1783 - accuracy: 0.9141 1152/6993 [===>..........................] - ETA: 0s - loss: 0.1311 - accuracy: 0.9618 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1440 - accuracy: 0.9619 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1307 - accuracy: 0.9667 3968/6993 [================>.............] - ETA: 0s - loss: 0.1257 - accuracy: 0.9677 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1324 - accuracy: 0.9657 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1302 - accuracy: 0.9652 6784/6993 [============================>.] - ETA: 0s - loss: 0.1295 - accuracy: 0.9634 6993/6993 [==============================] - 1s 72us/sample - loss: 0.1295 - accuracy: 0.9635 - val_loss: 0.4769 - val_accuracy: 0.8908 Epoch 34/500 128/6993 [..............................] - ETA: 0s - loss: 0.3040 - accuracy: 0.9297 896/6993 [==>...........................] - ETA: 0s - loss: 0.1489 - accuracy: 0.9621 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1493 - accuracy: 0.9593 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1362 - accuracy: 0.9643 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1540 - accuracy: 0.9609 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1448 - accuracy: 0.9618 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1486 - accuracy: 0.9618 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1446 - accuracy: 0.9623 6993/6993 [==============================] - 1s 72us/sample - loss: 0.1484 - accuracy: 0.9620 - val_loss: 0.3936 - val_accuracy: 0.9146 Epoch 35/500 128/6993 [..............................] - ETA: 0s - loss: 0.2060 - accuracy: 0.9297 896/6993 [==>...........................] - ETA: 0s - loss: 0.1447 - accuracy: 0.9565 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1361 - accuracy: 0.9604 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1177 - accuracy: 0.9660 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1244 - accuracy: 0.9648 4352/6993 [=================>............] - ETA: 0s - loss: 0.1315 - accuracy: 0.9625 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1322 - accuracy: 0.9621 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1324 - accuracy: 0.9616 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1307 - accuracy: 0.9621 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1315 - accuracy: 0.9617 - val_loss: 0.4548 - val_accuracy: 0.9019 Epoch 36/500 128/6993 [..............................] - ETA: 0s - loss: 0.1418 - accuracy: 0.9453 896/6993 [==>...........................] - ETA: 0s - loss: 0.1098 - accuracy: 0.9688 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1080 - accuracy: 0.9682 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1041 - accuracy: 0.9691 3456/6993 [=============>................] - ETA: 0s - loss: 0.1229 - accuracy: 0.9670 4352/6993 [=================>............] - ETA: 0s - loss: 0.1179 - accuracy: 0.9685 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1232 - accuracy: 0.9664 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1282 - accuracy: 0.9658 6912/6993 [============================>.] - ETA: 0s - loss: 0.1339 - accuracy: 0.9633 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1337 - accuracy: 0.9634 - val_loss: 0.3956 - val_accuracy: 0.9125 Epoch 37/500 128/6993 [..............................] - ETA: 0s - loss: 0.1504 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0779 - accuracy: 0.9788 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0884 - accuracy: 0.9724 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0963 - accuracy: 0.9688 3456/6993 [=============>................] - ETA: 0s - loss: 0.1058 - accuracy: 0.9664 4224/6993 [=================>............] - ETA: 0s - loss: 0.1147 - accuracy: 0.9673 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1126 - accuracy: 0.9676 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1104 - accuracy: 0.9691 6784/6993 [============================>.] - ETA: 0s - loss: 0.1116 - accuracy: 0.9680 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1118 - accuracy: 0.9683 - val_loss: 0.4125 - val_accuracy: 0.9120 Epoch 38/500 128/6993 [..............................] - ETA: 0s - loss: 0.0669 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0783 - accuracy: 0.9766 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0790 - accuracy: 0.9766 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1030 - accuracy: 0.9717 3456/6993 [=============>................] - ETA: 0s - loss: 0.1217 - accuracy: 0.9679 4224/6993 [=================>............] - ETA: 0s - loss: 0.1212 - accuracy: 0.9685 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1253 - accuracy: 0.9670 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1242 - accuracy: 0.9676 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1242 - accuracy: 0.9671 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1223 - accuracy: 0.9675 - val_loss: 0.4058 - val_accuracy: 0.9151 Epoch 39/500 128/6993 [..............................] - ETA: 0s - loss: 0.0645 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.1182 - accuracy: 0.9576 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1253 - accuracy: 0.9609 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1196 - accuracy: 0.9655 3328/6993 [=============>................] - ETA: 0s - loss: 0.1278 - accuracy: 0.9603 4224/6993 [=================>............] - ETA: 0s - loss: 0.1210 - accuracy: 0.9626 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1337 - accuracy: 0.9602 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1319 - accuracy: 0.9614 6784/6993 [============================>.] - ETA: 0s - loss: 0.1342 - accuracy: 0.9614 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1333 - accuracy: 0.9621 - val_loss: 0.4134 - val_accuracy: 0.9176 Epoch 40/500 128/6993 [..............................] - ETA: 0s - loss: 0.0752 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0925 - accuracy: 0.9743 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1017 - accuracy: 0.9700 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1058 - accuracy: 0.9715 3328/6993 [=============>................] - ETA: 0s - loss: 0.1042 - accuracy: 0.9727 4224/6993 [=================>............] - ETA: 0s - loss: 0.1006 - accuracy: 0.9735 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1040 - accuracy: 0.9724 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1170 - accuracy: 0.9693 6784/6993 [============================>.] - ETA: 0s - loss: 0.1174 - accuracy: 0.9685 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1227 - accuracy: 0.9683 - val_loss: 0.5378 - val_accuracy: 0.8984 Epoch 41/500 128/6993 [..............................] - ETA: 0s - loss: 0.0688 - accuracy: 0.9766 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0829 - accuracy: 0.9774 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1171 - accuracy: 0.9701 3200/6993 [============>.................] - ETA: 0s - loss: 0.1132 - accuracy: 0.9694 4096/6993 [================>.............] - ETA: 0s - loss: 0.1104 - accuracy: 0.9702 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1121 - accuracy: 0.9689 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1136 - accuracy: 0.9678 6993/6993 [==============================] - 0s 67us/sample - loss: 0.1153 - accuracy: 0.9678 - val_loss: 0.4719 - val_accuracy: 0.8953 Epoch 42/500 128/6993 [..............................] - ETA: 0s - loss: 0.1000 - accuracy: 0.9531 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1199 - accuracy: 0.9668 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1160 - accuracy: 0.9731 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1158 - accuracy: 0.9738 3968/6993 [================>.............] - ETA: 0s - loss: 0.1156 - accuracy: 0.9720 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1167 - accuracy: 0.9722 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1158 - accuracy: 0.9710 6912/6993 [============================>.] - ETA: 0s - loss: 0.1151 - accuracy: 0.9705 6993/6993 [==============================] - 0s 71us/sample - loss: 0.1154 - accuracy: 0.9701 - val_loss: 0.5098 - val_accuracy: 0.9004 Epoch 43/500 128/6993 [..............................] - ETA: 0s - loss: 0.0972 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0791 - accuracy: 0.9795 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1089 - accuracy: 0.9734 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1287 - accuracy: 0.9718 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1177 - accuracy: 0.9732 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1149 - accuracy: 0.9726 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1284 - accuracy: 0.9717 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1224 - accuracy: 0.9718 6993/6993 [==============================] - 0s 70us/sample - loss: 0.1214 - accuracy: 0.9710 - val_loss: 0.4533 - val_accuracy: 0.9105 Epoch 44/500 128/6993 [..............................] - ETA: 0s - loss: 0.0504 - accuracy: 0.9844 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0902 - accuracy: 0.9722 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0849 - accuracy: 0.9751 3072/6993 [============>.................] - ETA: 0s - loss: 0.0969 - accuracy: 0.9710 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0955 - accuracy: 0.9721 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0969 - accuracy: 0.9722 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0982 - accuracy: 0.9716 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0966 - accuracy: 0.9718 6993/6993 [==============================] - 1s 72us/sample - loss: 0.0958 - accuracy: 0.9720 - val_loss: 0.4658 - val_accuracy: 0.9055 Epoch 45/500 128/6993 [..............................] - ETA: 0s - loss: 0.1071 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0946 - accuracy: 0.9753 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1127 - accuracy: 0.9724 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1152 - accuracy: 0.9704 3328/6993 [=============>................] - ETA: 0s - loss: 0.1187 - accuracy: 0.9691 4096/6993 [================>.............] - ETA: 0s - loss: 0.1219 - accuracy: 0.9690 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1239 - accuracy: 0.9685 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1202 - accuracy: 0.9693 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1191 - accuracy: 0.9691 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1161 - accuracy: 0.9691 - val_loss: 0.4372 - val_accuracy: 0.9130 Epoch 46/500 128/6993 [..............................] - ETA: 0s - loss: 0.0924 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0655 - accuracy: 0.9788 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0648 - accuracy: 0.9802 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0767 - accuracy: 0.9794 3200/6993 [============>.................] - ETA: 0s - loss: 0.0904 - accuracy: 0.9756 3968/6993 [================>.............] - ETA: 0s - loss: 0.0960 - accuracy: 0.9748 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0974 - accuracy: 0.9745 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0941 - accuracy: 0.9754 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0965 - accuracy: 0.9757 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1012 - accuracy: 0.9749 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1033 - accuracy: 0.9743 - val_loss: 0.4440 - val_accuracy: 0.9176 Epoch 47/500 128/6993 [..............................] - ETA: 0s - loss: 0.0805 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0706 - accuracy: 0.9746 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0711 - accuracy: 0.9754 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0676 - accuracy: 0.9766 3072/6993 [============>.................] - ETA: 0s - loss: 0.0821 - accuracy: 0.9736 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0803 - accuracy: 0.9734 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0797 - accuracy: 0.9740 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0842 - accuracy: 0.9738 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0905 - accuracy: 0.9737 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0893 - accuracy: 0.9731 - val_loss: 0.4447 - val_accuracy: 0.9156 Epoch 48/500 128/6993 [..............................] - ETA: 0s - loss: 0.0716 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0893 - accuracy: 0.9732 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0946 - accuracy: 0.9749 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1016 - accuracy: 0.9727 3456/6993 [=============>................] - ETA: 0s - loss: 0.0987 - accuracy: 0.9722 4352/6993 [=================>............] - ETA: 0s - loss: 0.1014 - accuracy: 0.9713 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1019 - accuracy: 0.9717 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1007 - accuracy: 0.9723 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1013 - accuracy: 0.9724 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1003 - accuracy: 0.9728 - val_loss: 0.5310 - val_accuracy: 0.9024 Epoch 49/500 128/6993 [..............................] - ETA: 0s - loss: 0.1027 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.0703 - accuracy: 0.9734 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1042 - accuracy: 0.9766 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0978 - accuracy: 0.9766 3200/6993 [============>.................] - ETA: 0s - loss: 0.0950 - accuracy: 0.9756 3968/6993 [================>.............] - ETA: 0s - loss: 0.0923 - accuracy: 0.9768 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0904 - accuracy: 0.9772 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0926 - accuracy: 0.9771 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0868 - accuracy: 0.9778 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0888 - accuracy: 0.9775 - val_loss: 0.5628 - val_accuracy: 0.9090 Epoch 50/500 128/6993 [..............................] - ETA: 0s - loss: 0.2170 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1603 - accuracy: 0.9697 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1277 - accuracy: 0.9740 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1294 - accuracy: 0.9721 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1146 - accuracy: 0.9746 4352/6993 [=================>............] - ETA: 0s - loss: 0.1107 - accuracy: 0.9743 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1118 - accuracy: 0.9735 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1124 - accuracy: 0.9733 6912/6993 [============================>.] - ETA: 0s - loss: 0.1088 - accuracy: 0.9740 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1085 - accuracy: 0.9740 - val_loss: 0.4661 - val_accuracy: 0.9201 Epoch 51/500 128/6993 [..............................] - ETA: 0s - loss: 0.0153 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.1084 - accuracy: 0.9743 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1149 - accuracy: 0.9721 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1270 - accuracy: 0.9695 3456/6993 [=============>................] - ETA: 0s - loss: 0.1295 - accuracy: 0.9690 4352/6993 [=================>............] - ETA: 0s - loss: 0.1143 - accuracy: 0.9713 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1152 - accuracy: 0.9721 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1121 - accuracy: 0.9724 6912/6993 [============================>.] - ETA: 0s - loss: 0.1060 - accuracy: 0.9731 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1057 - accuracy: 0.9731 - val_loss: 0.4974 - val_accuracy: 0.9201 Epoch 52/500 128/6993 [..............................] - ETA: 0s - loss: 0.0670 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0599 - accuracy: 0.9795 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0740 - accuracy: 0.9782 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0761 - accuracy: 0.9788 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0792 - accuracy: 0.9794 4352/6993 [=================>............] - ETA: 0s - loss: 0.0801 - accuracy: 0.9784 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0856 - accuracy: 0.9771 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0883 - accuracy: 0.9767 6912/6993 [============================>.] - ETA: 0s - loss: 0.0894 - accuracy: 0.9767 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0916 - accuracy: 0.9764 - val_loss: 0.4857 - val_accuracy: 0.9161 Epoch 53/500 128/6993 [..............................] - ETA: 0s - loss: 0.1043 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0782 - accuracy: 0.9788 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0876 - accuracy: 0.9778 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0872 - accuracy: 0.9770 3328/6993 [=============>................] - ETA: 0s - loss: 0.0991 - accuracy: 0.9757 4224/6993 [=================>............] - ETA: 0s - loss: 0.0962 - accuracy: 0.9761 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0933 - accuracy: 0.9758 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0896 - accuracy: 0.9766 6784/6993 [============================>.] - ETA: 0s - loss: 0.0873 - accuracy: 0.9769 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0867 - accuracy: 0.9767 - val_loss: 0.4807 - val_accuracy: 0.9211 Epoch 54/500 128/6993 [..............................] - ETA: 0s - loss: 0.1019 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0766 - accuracy: 0.9788 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0792 - accuracy: 0.9808 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0780 - accuracy: 0.9777 3328/6993 [=============>................] - ETA: 0s - loss: 0.0717 - accuracy: 0.9796 3968/6993 [================>.............] - ETA: 0s - loss: 0.0810 - accuracy: 0.9796 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0849 - accuracy: 0.9785 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0901 - accuracy: 0.9773 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0946 - accuracy: 0.9769 6912/6993 [============================>.] - ETA: 0s - loss: 0.0926 - accuracy: 0.9769 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0918 - accuracy: 0.9770 - val_loss: 0.4472 - val_accuracy: 0.9242 Epoch 55/500 128/6993 [..............................] - ETA: 0s - loss: 0.1181 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0925 - accuracy: 0.9766 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1170 - accuracy: 0.9736 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1104 - accuracy: 0.9741 3328/6993 [=============>................] - ETA: 0s - loss: 0.1095 - accuracy: 0.9739 4096/6993 [================>.............] - ETA: 0s - loss: 0.1029 - accuracy: 0.9746 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0998 - accuracy: 0.9748 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0997 - accuracy: 0.9736 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0979 - accuracy: 0.9731 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0953 - accuracy: 0.9738 - val_loss: 0.3769 - val_accuracy: 0.9262 Epoch 56/500 128/6993 [..............................] - ETA: 0s - loss: 0.0232 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0834 - accuracy: 0.9810 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0683 - accuracy: 0.9810 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0647 - accuracy: 0.9803 3456/6993 [=============>................] - ETA: 0s - loss: 0.0803 - accuracy: 0.9777 4352/6993 [=================>............] - ETA: 0s - loss: 0.0800 - accuracy: 0.9761 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0804 - accuracy: 0.9766 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0904 - accuracy: 0.9752 6912/6993 [============================>.] - ETA: 0s - loss: 0.0889 - accuracy: 0.9751 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0881 - accuracy: 0.9754 - val_loss: 0.4166 - val_accuracy: 0.9257 Epoch 57/500 128/6993 [..............................] - ETA: 0s - loss: 0.0423 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0707 - accuracy: 0.9821 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0843 - accuracy: 0.9771 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0926 - accuracy: 0.9758 3328/6993 [=============>................] - ETA: 0s - loss: 0.0902 - accuracy: 0.9739 4224/6993 [=================>............] - ETA: 0s - loss: 0.0860 - accuracy: 0.9751 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0859 - accuracy: 0.9754 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0869 - accuracy: 0.9754 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0918 - accuracy: 0.9758 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0904 - accuracy: 0.9763 - val_loss: 0.4622 - val_accuracy: 0.9186 Epoch 58/500 128/6993 [..............................] - ETA: 0s - loss: 0.0491 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0585 - accuracy: 0.9821 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0559 - accuracy: 0.9826 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0698 - accuracy: 0.9800 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0669 - accuracy: 0.9813 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0663 - accuracy: 0.9806 4352/6993 [=================>............] - ETA: 0s - loss: 0.0707 - accuracy: 0.9802 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0764 - accuracy: 0.9799 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0818 - accuracy: 0.9788 6784/6993 [============================>.] - ETA: 0s - loss: 0.0780 - accuracy: 0.9794 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0814 - accuracy: 0.9784 - val_loss: 0.4520 - val_accuracy: 0.9156 Epoch 59/500 128/6993 [..............................] - ETA: 0s - loss: 0.0328 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0973 - accuracy: 0.9766 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0812 - accuracy: 0.9797 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0716 - accuracy: 0.9833 3328/6993 [=============>................] - ETA: 0s - loss: 0.0740 - accuracy: 0.9832 4224/6993 [=================>............] - ETA: 0s - loss: 0.0857 - accuracy: 0.9822 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0934 - accuracy: 0.9812 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0898 - accuracy: 0.9810 6784/6993 [============================>.] - ETA: 0s - loss: 0.0890 - accuracy: 0.9805 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0899 - accuracy: 0.9803 - val_loss: 0.5203 - val_accuracy: 0.9130 Epoch 60/500 128/6993 [..............................] - ETA: 0s - loss: 0.2521 - accuracy: 0.9531 896/6993 [==>...........................] - ETA: 0s - loss: 0.1575 - accuracy: 0.9665 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1180 - accuracy: 0.9743 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1030 - accuracy: 0.9770 3456/6993 [=============>................] - ETA: 0s - loss: 0.0955 - accuracy: 0.9792 4224/6993 [=================>............] - ETA: 0s - loss: 0.0899 - accuracy: 0.9794 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0982 - accuracy: 0.9764 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1037 - accuracy: 0.9766 6784/6993 [============================>.] - ETA: 0s - loss: 0.1035 - accuracy: 0.9749 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1019 - accuracy: 0.9754 - val_loss: 0.4354 - val_accuracy: 0.9247 Epoch 61/500 128/6993 [..............................] - ETA: 0s - loss: 0.0914 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0865 - accuracy: 0.9746 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0766 - accuracy: 0.9788 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0749 - accuracy: 0.9801 3456/6993 [=============>................] - ETA: 0s - loss: 0.0839 - accuracy: 0.9800 4224/6993 [=================>............] - ETA: 0s - loss: 0.0843 - accuracy: 0.9780 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0812 - accuracy: 0.9782 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0826 - accuracy: 0.9776 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0820 - accuracy: 0.9778 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0856 - accuracy: 0.9775 - val_loss: 0.4974 - val_accuracy: 0.9216 Epoch 62/500 128/6993 [..............................] - ETA: 0s - loss: 0.0327 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0758 - accuracy: 0.9814 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0720 - accuracy: 0.9799 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0759 - accuracy: 0.9784 3456/6993 [=============>................] - ETA: 0s - loss: 0.0828 - accuracy: 0.9774 4352/6993 [=================>............] - ETA: 0s - loss: 0.0872 - accuracy: 0.9768 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0899 - accuracy: 0.9768 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0892 - accuracy: 0.9771 6912/6993 [============================>.] - ETA: 0s - loss: 0.0890 - accuracy: 0.9764 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0883 - accuracy: 0.9765 - val_loss: 0.4146 - val_accuracy: 0.9247 Epoch 63/500 128/6993 [..............................] - ETA: 0s - loss: 0.0244 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0549 - accuracy: 0.9788 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0849 - accuracy: 0.9777 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0877 - accuracy: 0.9789 3456/6993 [=============>................] - ETA: 0s - loss: 0.0860 - accuracy: 0.9800 4224/6993 [=================>............] - ETA: 0s - loss: 0.0814 - accuracy: 0.9811 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0840 - accuracy: 0.9807 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0848 - accuracy: 0.9815 6784/6993 [============================>.] - ETA: 0s - loss: 0.0823 - accuracy: 0.9819 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0805 - accuracy: 0.9821 - val_loss: 0.5293 - val_accuracy: 0.9171 Epoch 64/500 128/6993 [..............................] - ETA: 0s - loss: 0.0314 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0789 - accuracy: 0.9732 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0750 - accuracy: 0.9760 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0692 - accuracy: 0.9786 3200/6993 [============>.................] - ETA: 0s - loss: 0.0677 - accuracy: 0.9778 4096/6993 [================>.............] - ETA: 0s - loss: 0.0802 - accuracy: 0.9771 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0786 - accuracy: 0.9780 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0810 - accuracy: 0.9780 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0809 - accuracy: 0.9778 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0814 - accuracy: 0.9777 - val_loss: 0.5163 - val_accuracy: 0.9267 Epoch 65/500 128/6993 [..............................] - ETA: 0s - loss: 0.0172 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0724 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0726 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0704 - accuracy: 0.9840 3456/6993 [=============>................] - ETA: 0s - loss: 0.0731 - accuracy: 0.9823 4352/6993 [=================>............] - ETA: 0s - loss: 0.0811 - accuracy: 0.9809 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0774 - accuracy: 0.9820 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0804 - accuracy: 0.9806 6784/6993 [============================>.] - ETA: 0s - loss: 0.0820 - accuracy: 0.9795 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0807 - accuracy: 0.9800 - val_loss: 0.5296 - val_accuracy: 0.9206 Epoch 66/500 128/6993 [..............................] - ETA: 0s - loss: 0.0591 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0930 - accuracy: 0.9821 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0799 - accuracy: 0.9827 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0757 - accuracy: 0.9832 3328/6993 [=============>................] - ETA: 0s - loss: 0.0808 - accuracy: 0.9823 4224/6993 [=================>............] - ETA: 0s - loss: 0.0815 - accuracy: 0.9806 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0850 - accuracy: 0.9794 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0900 - accuracy: 0.9783 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0877 - accuracy: 0.9782 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0878 - accuracy: 0.9785 - val_loss: 0.4851 - val_accuracy: 0.9232 Epoch 67/500 128/6993 [..............................] - ETA: 0s - loss: 0.0178 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0219 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0283 - accuracy: 0.9886 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0537 - accuracy: 0.9832 3200/6993 [============>.................] - ETA: 0s - loss: 0.0750 - accuracy: 0.9825 3968/6993 [================>.............] - ETA: 0s - loss: 0.0674 - accuracy: 0.9839 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0766 - accuracy: 0.9821 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0862 - accuracy: 0.9820 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0887 - accuracy: 0.9812 6912/6993 [============================>.] - ETA: 0s - loss: 0.0870 - accuracy: 0.9810 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0869 - accuracy: 0.9811 - val_loss: 0.4780 - val_accuracy: 0.9237 Epoch 68/500 128/6993 [..............................] - ETA: 0s - loss: 0.0458 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0591 - accuracy: 0.9754 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0679 - accuracy: 0.9754 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0807 - accuracy: 0.9766 3328/6993 [=============>................] - ETA: 0s - loss: 0.0887 - accuracy: 0.9772 4096/6993 [================>.............] - ETA: 0s - loss: 0.0910 - accuracy: 0.9758 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0908 - accuracy: 0.9759 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0869 - accuracy: 0.9760 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0937 - accuracy: 0.9767 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0918 - accuracy: 0.9768 - val_loss: 0.4758 - val_accuracy: 0.9232 Epoch 69/500 128/6993 [..............................] - ETA: 0s - loss: 0.0498 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0875 - accuracy: 0.9754 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0925 - accuracy: 0.9766 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0973 - accuracy: 0.9762 3456/6993 [=============>................] - ETA: 0s - loss: 0.0928 - accuracy: 0.9763 4224/6993 [=================>............] - ETA: 0s - loss: 0.0882 - accuracy: 0.9766 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0873 - accuracy: 0.9771 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0856 - accuracy: 0.9782 6784/6993 [============================>.] - ETA: 0s - loss: 0.0863 - accuracy: 0.9782 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0869 - accuracy: 0.9781 - val_loss: 0.4582 - val_accuracy: 0.9206 Epoch 70/500 128/6993 [..............................] - ETA: 0s - loss: 0.0741 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0432 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0437 - accuracy: 0.9866 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0419 - accuracy: 0.9870 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0463 - accuracy: 0.9871 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0573 - accuracy: 0.9847 4224/6993 [=================>............] - ETA: 0s - loss: 0.0558 - accuracy: 0.9844 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0617 - accuracy: 0.9829 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0676 - accuracy: 0.9819 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0709 - accuracy: 0.9812 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0741 - accuracy: 0.9816 - val_loss: 0.5422 - val_accuracy: 0.9211 Epoch 71/500 128/6993 [..............................] - ETA: 0s - loss: 0.0068 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0701 - accuracy: 0.9855 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0647 - accuracy: 0.9856 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0685 - accuracy: 0.9836 3328/6993 [=============>................] - ETA: 0s - loss: 0.0717 - accuracy: 0.9841 4096/6993 [================>.............] - ETA: 0s - loss: 0.0651 - accuracy: 0.9846 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0665 - accuracy: 0.9842 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0767 - accuracy: 0.9837 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0779 - accuracy: 0.9833 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0783 - accuracy: 0.9834 - val_loss: 0.5173 - val_accuracy: 0.9216 Epoch 72/500 128/6993 [..............................] - ETA: 0s - loss: 0.0410 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0420 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0749 - accuracy: 0.9838 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0780 - accuracy: 0.9824 3456/6993 [=============>................] - ETA: 0s - loss: 0.0698 - accuracy: 0.9847 4352/6993 [=================>............] - ETA: 0s - loss: 0.0794 - accuracy: 0.9814 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0730 - accuracy: 0.9821 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0700 - accuracy: 0.9822 6912/6993 [============================>.] - ETA: 0s - loss: 0.0756 - accuracy: 0.9815 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0757 - accuracy: 0.9813 - val_loss: 0.5602 - val_accuracy: 0.9171 Epoch 73/500 128/6993 [..............................] - ETA: 0s - loss: 0.0237 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0983 - accuracy: 0.9810 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0711 - accuracy: 0.9838 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0661 - accuracy: 0.9860 3072/6993 [============>.................] - ETA: 0s - loss: 0.0653 - accuracy: 0.9850 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0653 - accuracy: 0.9839 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0862 - accuracy: 0.9817 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0812 - accuracy: 0.9817 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0813 - accuracy: 0.9815 6912/6993 [============================>.] - ETA: 0s - loss: 0.0859 - accuracy: 0.9808 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0880 - accuracy: 0.9808 - val_loss: 0.5273 - val_accuracy: 0.9196 Epoch 74/500 128/6993 [..............................] - ETA: 0s - loss: 0.0992 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0722 - accuracy: 0.9821 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0621 - accuracy: 0.9838 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0715 - accuracy: 0.9828 3456/6993 [=============>................] - ETA: 0s - loss: 0.0708 - accuracy: 0.9818 4352/6993 [=================>............] - ETA: 0s - loss: 0.0707 - accuracy: 0.9816 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0674 - accuracy: 0.9817 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0679 - accuracy: 0.9819 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0738 - accuracy: 0.9811 - val_loss: 0.5061 - val_accuracy: 0.9226 Epoch 75/500 128/6993 [..............................] - ETA: 0s - loss: 0.2944 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.1008 - accuracy: 0.9788 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0983 - accuracy: 0.9805 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0838 - accuracy: 0.9829 3456/6993 [=============>................] - ETA: 0s - loss: 0.0840 - accuracy: 0.9826 4352/6993 [=================>............] - ETA: 0s - loss: 0.0755 - accuracy: 0.9837 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0744 - accuracy: 0.9842 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0717 - accuracy: 0.9840 6912/6993 [============================>.] - ETA: 0s - loss: 0.0734 - accuracy: 0.9838 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0744 - accuracy: 0.9834 - val_loss: 0.5163 - val_accuracy: 0.9186 Epoch 76/500 128/6993 [..............................] - ETA: 0s - loss: 0.0502 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1069 - accuracy: 0.9777 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0727 - accuracy: 0.9849 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0624 - accuracy: 0.9855 3456/6993 [=============>................] - ETA: 0s - loss: 0.0649 - accuracy: 0.9829 4352/6993 [=================>............] - ETA: 0s - loss: 0.0679 - accuracy: 0.9832 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0710 - accuracy: 0.9821 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0724 - accuracy: 0.9809 6784/6993 [============================>.] - ETA: 0s - loss: 0.0689 - accuracy: 0.9814 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0697 - accuracy: 0.9816 - val_loss: 0.5599 - val_accuracy: 0.9146 Epoch 77/500 128/6993 [..............................] - ETA: 0s - loss: 0.0683 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0845 - accuracy: 0.9777 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1265 - accuracy: 0.9772 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1155 - accuracy: 0.9778 3200/6993 [============>.................] - ETA: 0s - loss: 0.0987 - accuracy: 0.9791 4096/6993 [================>.............] - ETA: 0s - loss: 0.0932 - accuracy: 0.9795 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0897 - accuracy: 0.9790 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0852 - accuracy: 0.9801 6784/6993 [============================>.] - ETA: 0s - loss: 0.0811 - accuracy: 0.9808 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0837 - accuracy: 0.9806 - val_loss: 0.5578 - val_accuracy: 0.9171 Epoch 78/500 128/6993 [..............................] - ETA: 0s - loss: 0.1621 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0571 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0696 - accuracy: 0.9816 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0653 - accuracy: 0.9820 3456/6993 [=============>................] - ETA: 0s - loss: 0.0568 - accuracy: 0.9838 4352/6993 [=================>............] - ETA: 0s - loss: 0.0595 - accuracy: 0.9832 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0730 - accuracy: 0.9812 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0776 - accuracy: 0.9806 6784/6993 [============================>.] - ETA: 0s - loss: 0.0801 - accuracy: 0.9804 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0794 - accuracy: 0.9803 - val_loss: 0.5045 - val_accuracy: 0.9237 Epoch 79/500 128/6993 [..............................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0546 - accuracy: 0.9883 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0742 - accuracy: 0.9856 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0828 - accuracy: 0.9852 3328/6993 [=============>................] - ETA: 0s - loss: 0.0803 - accuracy: 0.9868 4096/6993 [================>.............] - ETA: 0s - loss: 0.0748 - accuracy: 0.9863 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0857 - accuracy: 0.9850 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0848 - accuracy: 0.9847 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0802 - accuracy: 0.9853 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0773 - accuracy: 0.9857 - val_loss: 0.5000 - val_accuracy: 0.9267 Epoch 80/500 128/6993 [..............................] - ETA: 0s - loss: 0.0467 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0328 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0739 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0828 - accuracy: 0.9816 3456/6993 [=============>................] - ETA: 0s - loss: 0.0695 - accuracy: 0.9835 4224/6993 [=================>............] - ETA: 0s - loss: 0.0673 - accuracy: 0.9839 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0749 - accuracy: 0.9824 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0779 - accuracy: 0.9818 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0822 - accuracy: 0.9811 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0810 - accuracy: 0.9816 - val_loss: 0.4747 - val_accuracy: 0.9221 Epoch 81/500 128/6993 [..............................] - ETA: 0s - loss: 0.1312 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0794 - accuracy: 0.9834 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0679 - accuracy: 0.9855 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0864 - accuracy: 0.9844 3456/6993 [=============>................] - ETA: 0s - loss: 0.0878 - accuracy: 0.9847 4352/6993 [=================>............] - ETA: 0s - loss: 0.0785 - accuracy: 0.9853 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0856 - accuracy: 0.9836 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0846 - accuracy: 0.9844 6784/6993 [============================>.] - ETA: 0s - loss: 0.0833 - accuracy: 0.9842 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0879 - accuracy: 0.9838 - val_loss: 0.4880 - val_accuracy: 0.9166 Epoch 82/500 128/6993 [..............................] - ETA: 0s - loss: 0.0232 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0871 - accuracy: 0.9777 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0813 - accuracy: 0.9766 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0717 - accuracy: 0.9793 3328/6993 [=============>................] - ETA: 0s - loss: 0.0738 - accuracy: 0.9811 4224/6993 [=================>............] - ETA: 0s - loss: 0.0751 - accuracy: 0.9801 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0742 - accuracy: 0.9820 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0698 - accuracy: 0.9827 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0718 - accuracy: 0.9830 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0701 - accuracy: 0.9833 - val_loss: 0.5129 - val_accuracy: 0.9297 Epoch 83/500 128/6993 [..............................] - ETA: 0s - loss: 0.1185 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0664 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0615 - accuracy: 0.9850 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0670 - accuracy: 0.9852 3328/6993 [=============>................] - ETA: 0s - loss: 0.0827 - accuracy: 0.9835 4224/6993 [=================>............] - ETA: 0s - loss: 0.0768 - accuracy: 0.9841 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0757 - accuracy: 0.9848 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0755 - accuracy: 0.9845 6912/6993 [============================>.] - ETA: 0s - loss: 0.0784 - accuracy: 0.9845 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0777 - accuracy: 0.9846 - val_loss: 0.4760 - val_accuracy: 0.9312 Epoch 84/500 128/6993 [..............................] - ETA: 0s - loss: 0.0645 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0419 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0674 - accuracy: 0.9892 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0598 - accuracy: 0.9879 3456/6993 [=============>................] - ETA: 0s - loss: 0.0590 - accuracy: 0.9870 4352/6993 [=================>............] - ETA: 0s - loss: 0.0619 - accuracy: 0.9862 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0738 - accuracy: 0.9851 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0685 - accuracy: 0.9859 6912/6993 [============================>.] - ETA: 0s - loss: 0.0691 - accuracy: 0.9850 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0683 - accuracy: 0.9851 - val_loss: 0.5469 - val_accuracy: 0.9282 Epoch 85/500 128/6993 [..............................] - ETA: 0s - loss: 0.0097 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0818 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0604 - accuracy: 0.9866 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0499 - accuracy: 0.9874 3456/6993 [=============>................] - ETA: 0s - loss: 0.0699 - accuracy: 0.9847 4352/6993 [=================>............] - ETA: 0s - loss: 0.0645 - accuracy: 0.9853 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0624 - accuracy: 0.9848 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0687 - accuracy: 0.9827 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0706 - accuracy: 0.9824 - val_loss: 0.4739 - val_accuracy: 0.9176 Epoch 86/500 128/6993 [..............................] - ETA: 0s - loss: 0.0544 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0552 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0770 - accuracy: 0.9816 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0691 - accuracy: 0.9848 3200/6993 [============>.................] - ETA: 0s - loss: 0.0718 - accuracy: 0.9844 3968/6993 [================>.............] - ETA: 0s - loss: 0.0717 - accuracy: 0.9826 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0741 - accuracy: 0.9823 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0699 - accuracy: 0.9835 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0727 - accuracy: 0.9826 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0716 - accuracy: 0.9834 - val_loss: 0.5726 - val_accuracy: 0.9191 Epoch 87/500 128/6993 [..............................] - ETA: 0s - loss: 0.0771 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0573 - accuracy: 0.9810 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0632 - accuracy: 0.9810 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0610 - accuracy: 0.9820 3456/6993 [=============>................] - ETA: 0s - loss: 0.0665 - accuracy: 0.9809 4352/6993 [=================>............] - ETA: 0s - loss: 0.0663 - accuracy: 0.9814 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0627 - accuracy: 0.9826 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0613 - accuracy: 0.9834 6912/6993 [============================>.] - ETA: 0s - loss: 0.0605 - accuracy: 0.9838 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0604 - accuracy: 0.9838 - val_loss: 0.5354 - val_accuracy: 0.9257 Epoch 88/500 128/6993 [..............................] - ETA: 0s - loss: 0.0692 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0549 - accuracy: 0.9873 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0794 - accuracy: 0.9839 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0702 - accuracy: 0.9847 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0863 - accuracy: 0.9841 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0828 - accuracy: 0.9837 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0844 - accuracy: 0.9825 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0794 - accuracy: 0.9832 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0755 - accuracy: 0.9836 - val_loss: 0.6303 - val_accuracy: 0.9206 Epoch 89/500 128/6993 [..............................] - ETA: 0s - loss: 0.0630 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.0560 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0878 - accuracy: 0.9810 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0879 - accuracy: 0.9814 3456/6993 [=============>................] - ETA: 0s - loss: 0.0865 - accuracy: 0.9797 4352/6993 [=================>............] - ETA: 0s - loss: 0.0835 - accuracy: 0.9795 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0811 - accuracy: 0.9798 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0779 - accuracy: 0.9802 6912/6993 [============================>.] - ETA: 0s - loss: 0.0760 - accuracy: 0.9809 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0772 - accuracy: 0.9808 - val_loss: 0.4591 - val_accuracy: 0.9363 Epoch 90/500 128/6993 [..............................] - ETA: 0s - loss: 0.0582 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0560 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0513 - accuracy: 0.9874 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0514 - accuracy: 0.9867 3328/6993 [=============>................] - ETA: 0s - loss: 0.0635 - accuracy: 0.9841 4224/6993 [=================>............] - ETA: 0s - loss: 0.0686 - accuracy: 0.9841 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0709 - accuracy: 0.9830 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0675 - accuracy: 0.9830 6784/6993 [============================>.] - ETA: 0s - loss: 0.0676 - accuracy: 0.9828 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0748 - accuracy: 0.9827 - val_loss: 0.4938 - val_accuracy: 0.9292 Epoch 91/500 128/6993 [..............................] - ETA: 0s - loss: 0.0775 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0640 - accuracy: 0.9833 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0558 - accuracy: 0.9866 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0635 - accuracy: 0.9859 3456/6993 [=============>................] - ETA: 0s - loss: 0.0624 - accuracy: 0.9852 4352/6993 [=================>............] - ETA: 0s - loss: 0.0721 - accuracy: 0.9851 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0711 - accuracy: 0.9848 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0700 - accuracy: 0.9849 6912/6993 [============================>.] - ETA: 0s - loss: 0.0747 - accuracy: 0.9838 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0740 - accuracy: 0.9840 - val_loss: 0.4753 - val_accuracy: 0.9267 Epoch 92/500 128/6993 [..............................] - ETA: 0s - loss: 0.1366 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1231 - accuracy: 0.9824 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0985 - accuracy: 0.9838 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1069 - accuracy: 0.9824 3328/6993 [=============>................] - ETA: 0s - loss: 0.1068 - accuracy: 0.9811 4096/6993 [================>.............] - ETA: 0s - loss: 0.0928 - accuracy: 0.9832 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0933 - accuracy: 0.9833 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0878 - accuracy: 0.9840 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0840 - accuracy: 0.9844 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0793 - accuracy: 0.9847 - val_loss: 0.5712 - val_accuracy: 0.9302 Epoch 93/500 128/6993 [..............................] - ETA: 0s - loss: 0.0954 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0822 - accuracy: 0.9863 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0765 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0754 - accuracy: 0.9847 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0704 - accuracy: 0.9847 4352/6993 [=================>............] - ETA: 0s - loss: 0.0641 - accuracy: 0.9860 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0700 - accuracy: 0.9855 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0687 - accuracy: 0.9845 6912/6993 [============================>.] - ETA: 0s - loss: 0.0663 - accuracy: 0.9850 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0657 - accuracy: 0.9851 - val_loss: 0.5423 - val_accuracy: 0.9257 Epoch 94/500 128/6993 [..............................] - ETA: 0s - loss: 0.0245 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0800 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0901 - accuracy: 0.9838 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0886 - accuracy: 0.9820 3456/6993 [=============>................] - ETA: 0s - loss: 0.0871 - accuracy: 0.9806 4224/6993 [=================>............] - ETA: 0s - loss: 0.0902 - accuracy: 0.9806 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0796 - accuracy: 0.9824 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0743 - accuracy: 0.9837 6784/6993 [============================>.] - ETA: 0s - loss: 0.0716 - accuracy: 0.9835 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0724 - accuracy: 0.9834 - val_loss: 0.5587 - val_accuracy: 0.9272 Epoch 95/500 128/6993 [..............................] - ETA: 0s - loss: 0.0032 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0963 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1048 - accuracy: 0.9833 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0943 - accuracy: 0.9836 3456/6993 [=============>................] - ETA: 0s - loss: 0.0885 - accuracy: 0.9835 4224/6993 [=================>............] - ETA: 0s - loss: 0.0810 - accuracy: 0.9848 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0772 - accuracy: 0.9855 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0758 - accuracy: 0.9856 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0746 - accuracy: 0.9854 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0758 - accuracy: 0.9843 - val_loss: 0.5480 - val_accuracy: 0.9272 Epoch 96/500 128/6993 [..............................] - ETA: 0s - loss: 0.0520 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.1527 - accuracy: 0.9766 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1303 - accuracy: 0.9818 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1182 - accuracy: 0.9815 3328/6993 [=============>................] - ETA: 0s - loss: 0.1029 - accuracy: 0.9832 4224/6993 [=================>............] - ETA: 0s - loss: 0.0890 - accuracy: 0.9853 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0837 - accuracy: 0.9842 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0816 - accuracy: 0.9842 6784/6993 [============================>.] - ETA: 0s - loss: 0.0847 - accuracy: 0.9836 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0831 - accuracy: 0.9837 - val_loss: 0.5150 - val_accuracy: 0.9247 Epoch 97/500 128/6993 [..............................] - ETA: 0s - loss: 0.0324 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0654 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0601 - accuracy: 0.9837 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0495 - accuracy: 0.9863 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0539 - accuracy: 0.9855 3328/6993 [=============>................] - ETA: 0s - loss: 0.0486 - accuracy: 0.9859 4096/6993 [================>.............] - ETA: 0s - loss: 0.0478 - accuracy: 0.9868 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0472 - accuracy: 0.9863 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0524 - accuracy: 0.9862 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0573 - accuracy: 0.9854 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0609 - accuracy: 0.9851 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0606 - accuracy: 0.9854 - val_loss: 0.5028 - val_accuracy: 0.9297 Epoch 98/500 128/6993 [..............................] - ETA: 0s - loss: 0.0980 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0517 - accuracy: 0.9844 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0761 - accuracy: 0.9837 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0779 - accuracy: 0.9823 3200/6993 [============>.................] - ETA: 0s - loss: 0.0816 - accuracy: 0.9812 4096/6993 [================>.............] - ETA: 0s - loss: 0.0733 - accuracy: 0.9814 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0726 - accuracy: 0.9827 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0754 - accuracy: 0.9817 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0719 - accuracy: 0.9823 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0765 - accuracy: 0.9821 - val_loss: 0.4892 - val_accuracy: 0.9323 Epoch 99/500 128/6993 [..............................] - ETA: 0s - loss: 0.0635 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0515 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0690 - accuracy: 0.9849 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0637 - accuracy: 0.9863 3328/6993 [=============>................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9850 3968/6993 [================>.............] - ETA: 0s - loss: 0.0590 - accuracy: 0.9861 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0582 - accuracy: 0.9860 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0654 - accuracy: 0.9853 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0621 - accuracy: 0.9856 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0619 - accuracy: 0.9857 - val_loss: 0.6449 - val_accuracy: 0.9206 Epoch 100/500 128/6993 [..............................] - ETA: 0s - loss: 0.0060 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0778 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0631 - accuracy: 0.9894 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0655 - accuracy: 0.9875 3328/6993 [=============>................] - ETA: 0s - loss: 0.0803 - accuracy: 0.9856 4224/6993 [=================>............] - ETA: 0s - loss: 0.0752 - accuracy: 0.9851 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0742 - accuracy: 0.9852 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0756 - accuracy: 0.9847 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0732 - accuracy: 0.9851 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0745 - accuracy: 0.9847 - val_loss: 0.5614 - val_accuracy: 0.9216 Epoch 101/500 128/6993 [..............................] - ETA: 0s - loss: 0.1694 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0908 - accuracy: 0.9775 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1020 - accuracy: 0.9782 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0813 - accuracy: 0.9818 3456/6993 [=============>................] - ETA: 0s - loss: 0.0870 - accuracy: 0.9812 4224/6993 [=================>............] - ETA: 0s - loss: 0.0810 - accuracy: 0.9813 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0783 - accuracy: 0.9822 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0753 - accuracy: 0.9830 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0797 - accuracy: 0.9827 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0770 - accuracy: 0.9833 - val_loss: 0.5393 - val_accuracy: 0.9206 Epoch 102/500 128/6993 [..............................] - ETA: 0s - loss: 0.0203 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0857 - accuracy: 0.9854 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0904 - accuracy: 0.9855 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0861 - accuracy: 0.9840 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0790 - accuracy: 0.9860 4352/6993 [=================>............] - ETA: 0s - loss: 0.0877 - accuracy: 0.9867 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0842 - accuracy: 0.9870 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0803 - accuracy: 0.9862 6912/6993 [============================>.] - ETA: 0s - loss: 0.0878 - accuracy: 0.9857 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0875 - accuracy: 0.9857 - val_loss: 0.5228 - val_accuracy: 0.9226 Epoch 103/500 128/6993 [..............................] - ETA: 0s - loss: 0.0329 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0591 - accuracy: 0.9902 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0682 - accuracy: 0.9894 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0730 - accuracy: 0.9874 3456/6993 [=============>................] - ETA: 0s - loss: 0.0953 - accuracy: 0.9855 4224/6993 [=================>............] - ETA: 0s - loss: 0.0907 - accuracy: 0.9846 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0894 - accuracy: 0.9842 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0871 - accuracy: 0.9840 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0887 - accuracy: 0.9835 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0881 - accuracy: 0.9834 - val_loss: 0.4720 - val_accuracy: 0.9282 Epoch 104/500 128/6993 [..............................] - ETA: 0s - loss: 0.0263 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0373 - accuracy: 0.9888 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0368 - accuracy: 0.9902 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0550 - accuracy: 0.9865 3200/6993 [============>.................] - ETA: 0s - loss: 0.0521 - accuracy: 0.9881 4096/6993 [================>.............] - ETA: 0s - loss: 0.0571 - accuracy: 0.9878 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0586 - accuracy: 0.9868 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0668 - accuracy: 0.9845 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0659 - accuracy: 0.9842 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0639 - accuracy: 0.9844 - val_loss: 0.5759 - val_accuracy: 0.9242 Epoch 105/500 128/6993 [..............................] - ETA: 0s - loss: 0.0624 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0515 - accuracy: 0.9857 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0559 - accuracy: 0.9857 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0683 - accuracy: 0.9848 3072/6993 [============>.................] - ETA: 0s - loss: 0.0733 - accuracy: 0.9814 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0763 - accuracy: 0.9818 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0746 - accuracy: 0.9818 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0763 - accuracy: 0.9822 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0770 - accuracy: 0.9825 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0801 - accuracy: 0.9826 - val_loss: 0.5077 - val_accuracy: 0.9302 Epoch 106/500 128/6993 [..............................] - ETA: 0s - loss: 0.0718 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0477 - accuracy: 0.9911 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0556 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0478 - accuracy: 0.9885 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0466 - accuracy: 0.9883 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0633 - accuracy: 0.9871 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0639 - accuracy: 0.9876 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0624 - accuracy: 0.9871 6784/6993 [============================>.] - ETA: 0s - loss: 0.0681 - accuracy: 0.9870 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0682 - accuracy: 0.9868 - val_loss: 0.6182 - val_accuracy: 0.9242 Epoch 107/500 128/6993 [..............................] - ETA: 0s - loss: 0.0908 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.0683 - accuracy: 0.9810 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0724 - accuracy: 0.9794 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0587 - accuracy: 0.9840 3456/6993 [=============>................] - ETA: 0s - loss: 0.0535 - accuracy: 0.9858 4352/6993 [=================>............] - ETA: 0s - loss: 0.0625 - accuracy: 0.9848 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0685 - accuracy: 0.9844 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0699 - accuracy: 0.9845 6912/6993 [============================>.] - ETA: 0s - loss: 0.0671 - accuracy: 0.9850 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0668 - accuracy: 0.9850 - val_loss: 0.5797 - val_accuracy: 0.9257 Epoch 108/500 128/6993 [..............................] - ETA: 0s - loss: 0.0533 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0335 - accuracy: 0.9893 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0574 - accuracy: 0.9855 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0572 - accuracy: 0.9844 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0620 - accuracy: 0.9841 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0695 - accuracy: 0.9837 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0668 - accuracy: 0.9840 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0718 - accuracy: 0.9836 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0705 - accuracy: 0.9834 - val_loss: 0.5711 - val_accuracy: 0.9277 Epoch 109/500 128/6993 [..............................] - ETA: 0s - loss: 0.1049 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0608 - accuracy: 0.9883 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0562 - accuracy: 0.9896 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0651 - accuracy: 0.9872 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0688 - accuracy: 0.9863 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0632 - accuracy: 0.9866 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0688 - accuracy: 0.9859 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0658 - accuracy: 0.9858 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0661 - accuracy: 0.9853 - val_loss: 0.6061 - val_accuracy: 0.9257 Epoch 110/500 128/6993 [..............................] - ETA: 0s - loss: 0.0461 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0598 - accuracy: 0.9870 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0751 - accuracy: 0.9832 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0846 - accuracy: 0.9815 3200/6993 [============>.................] - ETA: 0s - loss: 0.0868 - accuracy: 0.9825 4096/6993 [================>.............] - ETA: 0s - loss: 0.0831 - accuracy: 0.9829 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0736 - accuracy: 0.9842 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0700 - accuracy: 0.9840 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0704 - accuracy: 0.9836 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0709 - accuracy: 0.9834 - val_loss: 0.5182 - val_accuracy: 0.9292 Epoch 111/500 128/6993 [..............................] - ETA: 0s - loss: 0.0416 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0638 - accuracy: 0.9818 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0891 - accuracy: 0.9798 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0735 - accuracy: 0.9836 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0792 - accuracy: 0.9834 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0694 - accuracy: 0.9852 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0670 - accuracy: 0.9844 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0659 - accuracy: 0.9859 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0719 - accuracy: 0.9850 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0730 - accuracy: 0.9846 - val_loss: 0.5532 - val_accuracy: 0.9221 Epoch 112/500 128/6993 [..............................] - ETA: 0s - loss: 0.0061 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0186 - accuracy: 0.9933 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0331 - accuracy: 0.9905 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0378 - accuracy: 0.9892 3456/6993 [=============>................] - ETA: 0s - loss: 0.0417 - accuracy: 0.9887 3968/6993 [================>.............] - ETA: 0s - loss: 0.0411 - accuracy: 0.9887 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0401 - accuracy: 0.9887 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0457 - accuracy: 0.9884 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0507 - accuracy: 0.9878 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0569 - accuracy: 0.9868 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0551 - accuracy: 0.9870 - val_loss: 0.5927 - val_accuracy: 0.9262 Epoch 113/500 128/6993 [..............................] - ETA: 0s - loss: 0.3167 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1024 - accuracy: 0.9854 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0710 - accuracy: 0.9891 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0811 - accuracy: 0.9862 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0761 - accuracy: 0.9858 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0692 - accuracy: 0.9859 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0840 - accuracy: 0.9844 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0807 - accuracy: 0.9842 6993/6993 [==============================] - 1s 77us/sample - loss: 0.0781 - accuracy: 0.9836 - val_loss: 0.5958 - val_accuracy: 0.9252 Epoch 114/500 128/6993 [..............................] - ETA: 0s - loss: 0.0062 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0567 - accuracy: 0.9821 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0444 - accuracy: 0.9850 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0588 - accuracy: 0.9848 3328/6993 [=============>................] - ETA: 0s - loss: 0.0599 - accuracy: 0.9856 3968/6993 [================>.............] - ETA: 0s - loss: 0.0654 - accuracy: 0.9854 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0655 - accuracy: 0.9856 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0627 - accuracy: 0.9860 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0595 - accuracy: 0.9863 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0576 - accuracy: 0.9867 - val_loss: 0.6324 - val_accuracy: 0.9277 Epoch 115/500 128/6993 [..............................] - ETA: 0s - loss: 0.0760 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0716 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0521 - accuracy: 0.9900 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0452 - accuracy: 0.9910 3456/6993 [=============>................] - ETA: 0s - loss: 0.0542 - accuracy: 0.9893 4352/6993 [=================>............] - ETA: 0s - loss: 0.0566 - accuracy: 0.9892 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0530 - accuracy: 0.9891 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0619 - accuracy: 0.9870 6912/6993 [============================>.] - ETA: 0s - loss: 0.0607 - accuracy: 0.9868 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0608 - accuracy: 0.9868 - val_loss: 0.6144 - val_accuracy: 0.9242 Epoch 116/500 128/6993 [..............................] - ETA: 0s - loss: 0.0038 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0686 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0635 - accuracy: 0.9862 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0673 - accuracy: 0.9852 3456/6993 [=============>................] - ETA: 0s - loss: 0.0675 - accuracy: 0.9855 4224/6993 [=================>............] - ETA: 0s - loss: 0.0741 - accuracy: 0.9860 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0724 - accuracy: 0.9861 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0776 - accuracy: 0.9855 6912/6993 [============================>.] - ETA: 0s - loss: 0.0806 - accuracy: 0.9847 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0816 - accuracy: 0.9844 - val_loss: 0.5369 - val_accuracy: 0.9282 Epoch 117/500 128/6993 [..............................] - ETA: 0s - loss: 0.1239 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0900 - accuracy: 0.9834 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0733 - accuracy: 0.9855 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0650 - accuracy: 0.9866 3456/6993 [=============>................] - ETA: 0s - loss: 0.0592 - accuracy: 0.9861 4352/6993 [=================>............] - ETA: 0s - loss: 0.0575 - accuracy: 0.9869 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0705 - accuracy: 0.9857 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0695 - accuracy: 0.9852 6912/6993 [============================>.] - ETA: 0s - loss: 0.0717 - accuracy: 0.9855 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0715 - accuracy: 0.9856 - val_loss: 0.5674 - val_accuracy: 0.9282 Epoch 118/500 128/6993 [..............................] - ETA: 0s - loss: 0.3055 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0735 - accuracy: 0.9902 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0717 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0804 - accuracy: 0.9877 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0725 - accuracy: 0.9869 4352/6993 [=================>............] - ETA: 0s - loss: 0.0708 - accuracy: 0.9858 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0729 - accuracy: 0.9849 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0717 - accuracy: 0.9844 6784/6993 [============================>.] - ETA: 0s - loss: 0.0761 - accuracy: 0.9841 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0751 - accuracy: 0.9843 - val_loss: 0.5553 - val_accuracy: 0.9267 Epoch 119/500 128/6993 [..............................] - ETA: 0s - loss: 0.0131 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0167 - accuracy: 0.9961 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0410 - accuracy: 0.9927 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0382 - accuracy: 0.9926 3456/6993 [=============>................] - ETA: 0s - loss: 0.0367 - accuracy: 0.9916 4352/6993 [=================>............] - ETA: 0s - loss: 0.0524 - accuracy: 0.9894 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0490 - accuracy: 0.9896 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0592 - accuracy: 0.9882 6784/6993 [============================>.] - ETA: 0s - loss: 0.0700 - accuracy: 0.9878 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0687 - accuracy: 0.9877 - val_loss: 0.6314 - val_accuracy: 0.9252 Epoch 120/500 128/6993 [..............................] - ETA: 0s - loss: 0.0100 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0741 - accuracy: 0.9821 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0603 - accuracy: 0.9874 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0781 - accuracy: 0.9864 3200/6993 [============>.................] - ETA: 0s - loss: 0.0932 - accuracy: 0.9853 3968/6993 [================>.............] - ETA: 0s - loss: 0.0839 - accuracy: 0.9869 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0844 - accuracy: 0.9863 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0744 - accuracy: 0.9874 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0695 - accuracy: 0.9876 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0768 - accuracy: 0.9868 - val_loss: 0.5752 - val_accuracy: 0.9317 Epoch 121/500 128/6993 [..............................] - ETA: 0s - loss: 0.0065 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0392 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0384 - accuracy: 0.9888 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0345 - accuracy: 0.9902 3456/6993 [=============>................] - ETA: 0s - loss: 0.0438 - accuracy: 0.9887 4352/6993 [=================>............] - ETA: 0s - loss: 0.0447 - accuracy: 0.9883 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0566 - accuracy: 0.9872 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0661 - accuracy: 0.9870 6784/6993 [============================>.] - ETA: 0s - loss: 0.0653 - accuracy: 0.9872 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0673 - accuracy: 0.9870 - val_loss: 0.6159 - val_accuracy: 0.9226 Epoch 122/500 128/6993 [..............................] - ETA: 0s - loss: 0.0159 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0228 - accuracy: 0.9944 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0255 - accuracy: 0.9933 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0404 - accuracy: 0.9922 3456/6993 [=============>................] - ETA: 0s - loss: 0.0423 - accuracy: 0.9902 4352/6993 [=================>............] - ETA: 0s - loss: 0.0382 - accuracy: 0.9903 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0423 - accuracy: 0.9899 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0536 - accuracy: 0.9880 6912/6993 [============================>.] - ETA: 0s - loss: 0.0570 - accuracy: 0.9867 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0578 - accuracy: 0.9866 - val_loss: 0.5684 - val_accuracy: 0.9242 Epoch 123/500 128/6993 [..............................] - ETA: 0s - loss: 0.0253 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0902 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1030 - accuracy: 0.9810 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0924 - accuracy: 0.9828 3456/6993 [=============>................] - ETA: 0s - loss: 0.0797 - accuracy: 0.9855 4352/6993 [=================>............] - ETA: 0s - loss: 0.0765 - accuracy: 0.9851 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0813 - accuracy: 0.9848 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0742 - accuracy: 0.9857 6784/6993 [============================>.] - ETA: 0s - loss: 0.0714 - accuracy: 0.9857 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0697 - accuracy: 0.9861 - val_loss: 0.6047 - val_accuracy: 0.9237 Epoch 124/500 128/6993 [..............................] - ETA: 0s - loss: 0.0166 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0265 - accuracy: 0.9933 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0275 - accuracy: 0.9935 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0509 - accuracy: 0.9922 3200/6993 [============>.................] - ETA: 0s - loss: 0.0645 - accuracy: 0.9894 3968/6993 [================>.............] - ETA: 0s - loss: 0.0726 - accuracy: 0.9871 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0693 - accuracy: 0.9866 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0656 - accuracy: 0.9873 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0621 - accuracy: 0.9880 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0677 - accuracy: 0.9874 - val_loss: 0.6533 - val_accuracy: 0.9267 Epoch 125/500 128/6993 [..............................] - ETA: 0s - loss: 0.3432 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1691 - accuracy: 0.9824 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1182 - accuracy: 0.9859 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1156 - accuracy: 0.9840 3456/6993 [=============>................] - ETA: 0s - loss: 0.1069 - accuracy: 0.9847 4352/6993 [=================>............] - ETA: 0s - loss: 0.0995 - accuracy: 0.9844 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0927 - accuracy: 0.9846 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0895 - accuracy: 0.9847 6784/6993 [============================>.] - ETA: 0s - loss: 0.0866 - accuracy: 0.9851 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0852 - accuracy: 0.9850 - val_loss: 0.6307 - val_accuracy: 0.9181 Epoch 126/500 128/6993 [..............................] - ETA: 0s - loss: 0.0107 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0750 - accuracy: 0.9863 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0651 - accuracy: 0.9855 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0589 - accuracy: 0.9859 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0576 - accuracy: 0.9863 4352/6993 [=================>............] - ETA: 0s - loss: 0.0567 - accuracy: 0.9867 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0651 - accuracy: 0.9867 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0637 - accuracy: 0.9868 6912/6993 [============================>.] - ETA: 0s - loss: 0.0637 - accuracy: 0.9865 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0630 - accuracy: 0.9867 - val_loss: 0.6075 - val_accuracy: 0.9262 Epoch 127/500 128/6993 [..............................] - ETA: 0s - loss: 0.0203 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0904 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1169 - accuracy: 0.9874 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1111 - accuracy: 0.9867 3456/6993 [=============>................] - ETA: 0s - loss: 0.0927 - accuracy: 0.9867 4224/6993 [=================>............] - ETA: 0s - loss: 0.0807 - accuracy: 0.9875 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0882 - accuracy: 0.9867 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0876 - accuracy: 0.9860 6784/6993 [============================>.] - ETA: 0s - loss: 0.0830 - accuracy: 0.9860 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0809 - accuracy: 0.9863 - val_loss: 0.7272 - val_accuracy: 0.9257 Epoch 128/500 128/6993 [..............................] - ETA: 0s - loss: 0.0613 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0472 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0895 - accuracy: 0.9872 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1039 - accuracy: 0.9844 3200/6993 [============>.................] - ETA: 0s - loss: 0.1013 - accuracy: 0.9844 3968/6993 [================>.............] - ETA: 0s - loss: 0.0994 - accuracy: 0.9841 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1065 - accuracy: 0.9838 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1063 - accuracy: 0.9833 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1002 - accuracy: 0.9839 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0991 - accuracy: 0.9843 - val_loss: 0.5793 - val_accuracy: 0.9292 Epoch 129/500 128/6993 [..............................] - ETA: 0s - loss: 0.0949 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0375 - accuracy: 0.9933 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0416 - accuracy: 0.9916 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0405 - accuracy: 0.9910 3328/6993 [=============>................] - ETA: 0s - loss: 0.0513 - accuracy: 0.9898 4224/6993 [=================>............] - ETA: 0s - loss: 0.0631 - accuracy: 0.9893 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0635 - accuracy: 0.9891 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0799 - accuracy: 0.9887 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0893 - accuracy: 0.9883 6784/6993 [============================>.] - ETA: 0s - loss: 0.0852 - accuracy: 0.9884 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0870 - accuracy: 0.9881 - val_loss: 0.6380 - val_accuracy: 0.9206 Epoch 130/500 128/6993 [..............................] - ETA: 0s - loss: 0.0018 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0228 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0322 - accuracy: 0.9893 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0433 - accuracy: 0.9899 3072/6993 [============>.................] - ETA: 0s - loss: 0.0557 - accuracy: 0.9886 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0572 - accuracy: 0.9880 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0574 - accuracy: 0.9879 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0588 - accuracy: 0.9879 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0597 - accuracy: 0.9880 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0548 - accuracy: 0.9893 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0536 - accuracy: 0.9897 - val_loss: 0.6662 - val_accuracy: 0.9287 Epoch 131/500 128/6993 [..............................] - ETA: 0s - loss: 0.0256 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1239 - accuracy: 0.9818 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0903 - accuracy: 0.9857 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0762 - accuracy: 0.9861 3200/6993 [============>.................] - ETA: 0s - loss: 0.0803 - accuracy: 0.9841 4096/6993 [================>.............] - ETA: 0s - loss: 0.0792 - accuracy: 0.9851 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0815 - accuracy: 0.9866 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0782 - accuracy: 0.9863 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0796 - accuracy: 0.9866 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0769 - accuracy: 0.9864 - val_loss: 0.5598 - val_accuracy: 0.9282 Epoch 132/500 128/6993 [..............................] - ETA: 0s - loss: 0.0098 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0481 - accuracy: 0.9893 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1042 - accuracy: 0.9812 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0882 - accuracy: 0.9822 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0847 - accuracy: 0.9830 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1009 - accuracy: 0.9826 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0912 - accuracy: 0.9833 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0874 - accuracy: 0.9836 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0949 - accuracy: 0.9833 - val_loss: 0.5286 - val_accuracy: 0.9151 Epoch 133/500 128/6993 [..............................] - ETA: 0s - loss: 0.0221 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1168 - accuracy: 0.9821 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0802 - accuracy: 0.9856 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0891 - accuracy: 0.9860 3200/6993 [============>.................] - ETA: 0s - loss: 0.0858 - accuracy: 0.9844 3968/6993 [================>.............] - ETA: 0s - loss: 0.0855 - accuracy: 0.9834 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0915 - accuracy: 0.9837 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0850 - accuracy: 0.9840 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0868 - accuracy: 0.9842 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0884 - accuracy: 0.9847 - val_loss: 0.5728 - val_accuracy: 0.9216 Epoch 134/500 128/6993 [..............................] - ETA: 0s - loss: 0.1268 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0629 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0850 - accuracy: 0.9877 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0771 - accuracy: 0.9874 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0833 - accuracy: 0.9877 4352/6993 [=================>............] - ETA: 0s - loss: 0.0862 - accuracy: 0.9862 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0897 - accuracy: 0.9859 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0937 - accuracy: 0.9850 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0878 - accuracy: 0.9854 - val_loss: 0.5935 - val_accuracy: 0.9206 Epoch 135/500 128/6993 [..............................] - ETA: 0s - loss: 0.0387 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0684 - accuracy: 0.9833 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0687 - accuracy: 0.9838 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0684 - accuracy: 0.9840 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0758 - accuracy: 0.9835 4352/6993 [=================>............] - ETA: 0s - loss: 0.0720 - accuracy: 0.9844 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0681 - accuracy: 0.9853 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0639 - accuracy: 0.9863 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0624 - accuracy: 0.9867 - val_loss: 0.6847 - val_accuracy: 0.9191 Epoch 136/500 128/6993 [..............................] - ETA: 0s - loss: 0.1586 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.0488 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0329 - accuracy: 0.9894 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0421 - accuracy: 0.9907 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0541 - accuracy: 0.9902 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0504 - accuracy: 0.9904 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0588 - accuracy: 0.9888 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0638 - accuracy: 0.9881 6912/6993 [============================>.] - ETA: 0s - loss: 0.0687 - accuracy: 0.9886 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0698 - accuracy: 0.9883 - val_loss: 0.5785 - val_accuracy: 0.9277 Epoch 137/500 128/6993 [..............................] - ETA: 0s - loss: 0.0825 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0786 - accuracy: 0.9795 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0855 - accuracy: 0.9802 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0759 - accuracy: 0.9820 3456/6993 [=============>................] - ETA: 0s - loss: 0.0728 - accuracy: 0.9821 4352/6993 [=================>............] - ETA: 0s - loss: 0.0822 - accuracy: 0.9828 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0893 - accuracy: 0.9827 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0925 - accuracy: 0.9825 6912/6993 [============================>.] - ETA: 0s - loss: 0.0909 - accuracy: 0.9829 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0901 - accuracy: 0.9830 - val_loss: 0.5183 - val_accuracy: 0.9323 Epoch 138/500 128/6993 [..............................] - ETA: 0s - loss: 0.0931 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0443 - accuracy: 0.9911 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0535 - accuracy: 0.9892 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0447 - accuracy: 0.9902 3328/6993 [=============>................] - ETA: 0s - loss: 0.0575 - accuracy: 0.9880 4224/6993 [=================>............] - ETA: 0s - loss: 0.0497 - accuracy: 0.9891 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0567 - accuracy: 0.9883 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0601 - accuracy: 0.9882 6912/6993 [============================>.] - ETA: 0s - loss: 0.0587 - accuracy: 0.9886 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0597 - accuracy: 0.9886 - val_loss: 0.6030 - val_accuracy: 0.9323 Epoch 139/500 128/6993 [..............................] - ETA: 0s - loss: 0.0180 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0724 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0684 - accuracy: 0.9874 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0650 - accuracy: 0.9848 3328/6993 [=============>................] - ETA: 0s - loss: 0.0620 - accuracy: 0.9853 4096/6993 [================>.............] - ETA: 0s - loss: 0.0594 - accuracy: 0.9861 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0553 - accuracy: 0.9866 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0569 - accuracy: 0.9861 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0589 - accuracy: 0.9863 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0578 - accuracy: 0.9863 - val_loss: 0.6833 - val_accuracy: 0.9262 Epoch 140/500 128/6993 [..............................] - ETA: 0s - loss: 0.0625 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0397 - accuracy: 0.9932 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0602 - accuracy: 0.9896 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0700 - accuracy: 0.9883 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0826 - accuracy: 0.9866 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0782 - accuracy: 0.9868 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0735 - accuracy: 0.9872 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0668 - accuracy: 0.9874 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0714 - accuracy: 0.9870 - val_loss: 0.6801 - val_accuracy: 0.9292 Epoch 141/500 128/6993 [..............................] - ETA: 0s - loss: 0.1939 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1412 - accuracy: 0.9854 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0984 - accuracy: 0.9855 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0791 - accuracy: 0.9870 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0699 - accuracy: 0.9880 4352/6993 [=================>............] - ETA: 0s - loss: 0.0773 - accuracy: 0.9874 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0690 - accuracy: 0.9876 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0794 - accuracy: 0.9863 6912/6993 [============================>.] - ETA: 0s - loss: 0.0774 - accuracy: 0.9868 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0767 - accuracy: 0.9870 - val_loss: 0.6864 - val_accuracy: 0.9226 Epoch 142/500 128/6993 [..............................] - ETA: 0s - loss: 0.1444 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1403 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1001 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1020 - accuracy: 0.9852 3456/6993 [=============>................] - ETA: 0s - loss: 0.0922 - accuracy: 0.9847 4352/6993 [=================>............] - ETA: 0s - loss: 0.0822 - accuracy: 0.9851 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0810 - accuracy: 0.9852 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0755 - accuracy: 0.9854 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0702 - accuracy: 0.9860 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0721 - accuracy: 0.9856 - val_loss: 0.6056 - val_accuracy: 0.9267 Epoch 143/500 128/6993 [..............................] - ETA: 0s - loss: 0.1929 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0534 - accuracy: 0.9922 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0419 - accuracy: 0.9915 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0408 - accuracy: 0.9909 3200/6993 [============>.................] - ETA: 0s - loss: 0.0412 - accuracy: 0.9903 4096/6993 [================>.............] - ETA: 0s - loss: 0.0501 - accuracy: 0.9895 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0539 - accuracy: 0.9889 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0885 - accuracy: 0.9852 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0845 - accuracy: 0.9850 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0811 - accuracy: 0.9854 - val_loss: 0.5831 - val_accuracy: 0.9292 Epoch 144/500 128/6993 [..............................] - ETA: 0s - loss: 0.1106 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0809 - accuracy: 0.9902 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1027 - accuracy: 0.9865 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0903 - accuracy: 0.9869 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0759 - accuracy: 0.9880 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0808 - accuracy: 0.9875 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0744 - accuracy: 0.9881 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0735 - accuracy: 0.9881 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0791 - accuracy: 0.9870 - val_loss: 0.6257 - val_accuracy: 0.9247 Epoch 145/500 128/6993 [..............................] - ETA: 0s - loss: 0.0138 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0413 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0746 - accuracy: 0.9872 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0866 - accuracy: 0.9844 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0692 - accuracy: 0.9869 4352/6993 [=================>............] - ETA: 0s - loss: 0.0660 - accuracy: 0.9874 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0674 - accuracy: 0.9870 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0726 - accuracy: 0.9857 6912/6993 [============================>.] - ETA: 0s - loss: 0.0731 - accuracy: 0.9855 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0738 - accuracy: 0.9856 - val_loss: 0.6627 - val_accuracy: 0.9307 Epoch 146/500 128/6993 [..............................] - ETA: 0s - loss: 0.0209 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0619 - accuracy: 0.9933 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0735 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0590 - accuracy: 0.9896 3456/6993 [=============>................] - ETA: 0s - loss: 0.0695 - accuracy: 0.9878 4352/6993 [=================>............] - ETA: 0s - loss: 0.0640 - accuracy: 0.9871 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0595 - accuracy: 0.9880 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0586 - accuracy: 0.9882 6912/6993 [============================>.] - ETA: 0s - loss: 0.0612 - accuracy: 0.9874 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0612 - accuracy: 0.9873 - val_loss: 0.6447 - val_accuracy: 0.9252 Epoch 147/500 128/6993 [..............................] - ETA: 0s - loss: 0.0665 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0713 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0877 - accuracy: 0.9866 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0828 - accuracy: 0.9859 3456/6993 [=============>................] - ETA: 0s - loss: 0.0683 - accuracy: 0.9867 4352/6993 [=================>............] - ETA: 0s - loss: 0.0675 - accuracy: 0.9862 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0718 - accuracy: 0.9859 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0699 - accuracy: 0.9864 6912/6993 [============================>.] - ETA: 0s - loss: 0.0689 - accuracy: 0.9868 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0683 - accuracy: 0.9868 - val_loss: 0.7639 - val_accuracy: 0.9221 Epoch 148/500 128/6993 [..............................] - ETA: 0s - loss: 0.1924 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9922 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0948 - accuracy: 0.9896 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0763 - accuracy: 0.9896 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0644 - accuracy: 0.9908 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0611 - accuracy: 0.9906 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0708 - accuracy: 0.9899 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0723 - accuracy: 0.9902 6784/6993 [============================>.] - ETA: 0s - loss: 0.0718 - accuracy: 0.9895 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0726 - accuracy: 0.9893 - val_loss: 0.7200 - val_accuracy: 0.9282 Epoch 149/500 128/6993 [..............................] - ETA: 0s - loss: 0.0240 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1112 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0808 - accuracy: 0.9855 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0896 - accuracy: 0.9859 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0821 - accuracy: 0.9872 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0782 - accuracy: 0.9873 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0743 - accuracy: 0.9874 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0721 - accuracy: 0.9871 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0686 - accuracy: 0.9878 - val_loss: 0.7003 - val_accuracy: 0.9272 Epoch 150/500 128/6993 [..............................] - ETA: 0s - loss: 0.0052 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0855 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0701 - accuracy: 0.9868 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0642 - accuracy: 0.9863 3328/6993 [=============>................] - ETA: 0s - loss: 0.0610 - accuracy: 0.9856 4224/6993 [=================>............] - ETA: 0s - loss: 0.0557 - accuracy: 0.9875 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0610 - accuracy: 0.9871 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0602 - accuracy: 0.9873 6784/6993 [============================>.] - ETA: 0s - loss: 0.0674 - accuracy: 0.9869 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0691 - accuracy: 0.9866 - val_loss: 0.6714 - val_accuracy: 0.9297 Epoch 151/500 128/6993 [..............................] - ETA: 0s - loss: 0.1220 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0592 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0503 - accuracy: 0.9916 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0524 - accuracy: 0.9902 3328/6993 [=============>................] - ETA: 0s - loss: 0.0499 - accuracy: 0.9904 4224/6993 [=================>............] - ETA: 0s - loss: 0.0523 - accuracy: 0.9896 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0560 - accuracy: 0.9885 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0550 - accuracy: 0.9888 6784/6993 [============================>.] - ETA: 0s - loss: 0.0660 - accuracy: 0.9882 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0655 - accuracy: 0.9883 - val_loss: 0.7812 - val_accuracy: 0.9196 Epoch 152/500 128/6993 [..............................] - ETA: 0s - loss: 0.0280 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0252 - accuracy: 0.9909 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1157 - accuracy: 0.9832 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0981 - accuracy: 0.9848 3072/6993 [============>.................] - ETA: 0s - loss: 0.0973 - accuracy: 0.9837 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0963 - accuracy: 0.9833 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0873 - accuracy: 0.9846 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0908 - accuracy: 0.9840 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0857 - accuracy: 0.9854 6912/6993 [============================>.] - ETA: 0s - loss: 0.0833 - accuracy: 0.9857 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0831 - accuracy: 0.9856 - val_loss: 0.7091 - val_accuracy: 0.9302 Epoch 153/500 128/6993 [..............................] - ETA: 0s - loss: 0.1669 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0897 - accuracy: 0.9877 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0922 - accuracy: 0.9856 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0680 - accuracy: 0.9891 3456/6993 [=============>................] - ETA: 0s - loss: 0.0640 - accuracy: 0.9893 4224/6993 [=================>............] - ETA: 0s - loss: 0.0700 - accuracy: 0.9889 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0763 - accuracy: 0.9877 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0723 - accuracy: 0.9876 6784/6993 [============================>.] - ETA: 0s - loss: 0.0672 - accuracy: 0.9884 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0656 - accuracy: 0.9886 - val_loss: 0.7510 - val_accuracy: 0.9328 Epoch 154/500 128/6993 [..............................] - ETA: 0s - loss: 0.0215 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0552 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0886 - accuracy: 0.9856 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0764 - accuracy: 0.9859 3456/6993 [=============>................] - ETA: 0s - loss: 0.0664 - accuracy: 0.9881 4224/6993 [=================>............] - ETA: 0s - loss: 0.0748 - accuracy: 0.9884 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0848 - accuracy: 0.9881 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0848 - accuracy: 0.9879 6784/6993 [============================>.] - ETA: 0s - loss: 0.0836 - accuracy: 0.9881 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0828 - accuracy: 0.9880 - val_loss: 0.6819 - val_accuracy: 0.9302 Epoch 155/500 128/6993 [..............................] - ETA: 0s - loss: 0.6055 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1419 - accuracy: 0.9877 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1163 - accuracy: 0.9874 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0936 - accuracy: 0.9879 3456/6993 [=============>................] - ETA: 0s - loss: 0.1182 - accuracy: 0.9870 4224/6993 [=================>............] - ETA: 0s - loss: 0.1145 - accuracy: 0.9865 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1059 - accuracy: 0.9871 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1009 - accuracy: 0.9876 6784/6993 [============================>.] - ETA: 0s - loss: 0.1029 - accuracy: 0.9872 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1022 - accuracy: 0.9870 - val_loss: 0.6558 - val_accuracy: 0.9267 Epoch 156/500 128/6993 [..............................] - ETA: 0s - loss: 0.0191 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0602 - accuracy: 0.9857 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0467 - accuracy: 0.9892 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0481 - accuracy: 0.9897 3328/6993 [=============>................] - ETA: 0s - loss: 0.0516 - accuracy: 0.9886 4096/6993 [================>.............] - ETA: 0s - loss: 0.0553 - accuracy: 0.9890 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0583 - accuracy: 0.9887 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0563 - accuracy: 0.9887 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0593 - accuracy: 0.9886 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0605 - accuracy: 0.9884 - val_loss: 0.7336 - val_accuracy: 0.9328 Epoch 157/500 128/6993 [..............................] - ETA: 0s - loss: 0.0588 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0959 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0737 - accuracy: 0.9860 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0782 - accuracy: 0.9855 3456/6993 [=============>................] - ETA: 0s - loss: 0.0765 - accuracy: 0.9855 4224/6993 [=================>............] - ETA: 0s - loss: 0.0701 - accuracy: 0.9858 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0681 - accuracy: 0.9865 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0720 - accuracy: 0.9857 6784/6993 [============================>.] - ETA: 0s - loss: 0.0903 - accuracy: 0.9853 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0905 - accuracy: 0.9853 - val_loss: 0.6680 - val_accuracy: 0.9307 Epoch 158/500 128/6993 [..............................] - ETA: 0s - loss: 0.0370 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1202 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0850 - accuracy: 0.9898 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0786 - accuracy: 0.9877 3200/6993 [============>.................] - ETA: 0s - loss: 0.0820 - accuracy: 0.9875 4096/6993 [================>.............] - ETA: 0s - loss: 0.0767 - accuracy: 0.9875 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0791 - accuracy: 0.9862 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0772 - accuracy: 0.9861 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0831 - accuracy: 0.9851 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0819 - accuracy: 0.9850 - val_loss: 0.8439 - val_accuracy: 0.9171 Epoch 159/500 128/6993 [..............................] - ETA: 0s - loss: 0.0084 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0485 - accuracy: 0.9900 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0665 - accuracy: 0.9860 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0692 - accuracy: 0.9859 3456/6993 [=============>................] - ETA: 0s - loss: 0.0619 - accuracy: 0.9870 4352/6993 [=================>............] - ETA: 0s - loss: 0.0665 - accuracy: 0.9864 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0618 - accuracy: 0.9867 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0709 - accuracy: 0.9858 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0659 - accuracy: 0.9868 - val_loss: 0.7159 - val_accuracy: 0.9221 Epoch 160/500 128/6993 [..............................] - ETA: 0s - loss: 0.0077 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0921 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0703 - accuracy: 0.9872 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0587 - accuracy: 0.9881 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0610 - accuracy: 0.9877 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0608 - accuracy: 0.9888 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0588 - accuracy: 0.9881 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0566 - accuracy: 0.9885 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0662 - accuracy: 0.9880 - val_loss: 0.7524 - val_accuracy: 0.9333 Epoch 161/500 128/6993 [..............................] - ETA: 0s - loss: 0.0451 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0684 - accuracy: 0.9854 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0479 - accuracy: 0.9859 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0494 - accuracy: 0.9869 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0544 - accuracy: 0.9872 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0604 - accuracy: 0.9879 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0564 - accuracy: 0.9888 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0659 - accuracy: 0.9879 6784/6993 [============================>.] - ETA: 0s - loss: 0.0676 - accuracy: 0.9882 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0673 - accuracy: 0.9880 - val_loss: 0.6574 - val_accuracy: 0.9297 Epoch 162/500 128/6993 [..............................] - ETA: 0s - loss: 0.0819 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0955 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0686 - accuracy: 0.9892 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0639 - accuracy: 0.9900 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0867 - accuracy: 0.9895 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0950 - accuracy: 0.9888 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0931 - accuracy: 0.9886 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0915 - accuracy: 0.9874 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0862 - accuracy: 0.9879 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0838 - accuracy: 0.9879 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0888 - accuracy: 0.9878 - val_loss: 0.7153 - val_accuracy: 0.9257 Epoch 163/500 128/6993 [..............................] - ETA: 0s - loss: 0.0071 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0249 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0374 - accuracy: 0.9898 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0357 - accuracy: 0.9887 3456/6993 [=============>................] - ETA: 0s - loss: 0.0411 - accuracy: 0.9884 4224/6993 [=================>............] - ETA: 0s - loss: 0.0402 - accuracy: 0.9896 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0506 - accuracy: 0.9889 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0540 - accuracy: 0.9885 6784/6993 [============================>.] - ETA: 0s - loss: 0.0550 - accuracy: 0.9885 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0539 - accuracy: 0.9886 - val_loss: 0.7338 - val_accuracy: 0.9312 Epoch 164/500 128/6993 [..............................] - ETA: 0s - loss: 0.2693 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1005 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0845 - accuracy: 0.9877 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0772 - accuracy: 0.9870 3456/6993 [=============>................] - ETA: 0s - loss: 0.0773 - accuracy: 0.9870 4352/6993 [=================>............] - ETA: 0s - loss: 0.0695 - accuracy: 0.9878 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0707 - accuracy: 0.9870 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0735 - accuracy: 0.9862 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0706 - accuracy: 0.9868 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0677 - accuracy: 0.9873 - val_loss: 0.7222 - val_accuracy: 0.9323 Epoch 165/500 128/6993 [..............................] - ETA: 1s - loss: 0.0311 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1241 - accuracy: 0.9857 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0843 - accuracy: 0.9863 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0723 - accuracy: 0.9887 3200/6993 [============>.................] - ETA: 0s - loss: 0.0832 - accuracy: 0.9862 4096/6993 [================>.............] - ETA: 0s - loss: 0.0807 - accuracy: 0.9858 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0906 - accuracy: 0.9856 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0857 - accuracy: 0.9863 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0940 - accuracy: 0.9854 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0963 - accuracy: 0.9848 - val_loss: 0.6552 - val_accuracy: 0.9216 Epoch 166/500 128/6993 [..............................] - ETA: 0s - loss: 0.0317 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0436 - accuracy: 0.9922 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0443 - accuracy: 0.9916 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0728 - accuracy: 0.9910 3456/6993 [=============>................] - ETA: 0s - loss: 0.0672 - accuracy: 0.9910 4352/6993 [=================>............] - ETA: 0s - loss: 0.0659 - accuracy: 0.9899 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0593 - accuracy: 0.9905 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0558 - accuracy: 0.9910 6912/6993 [============================>.] - ETA: 0s - loss: 0.0539 - accuracy: 0.9907 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0582 - accuracy: 0.9903 - val_loss: 0.7639 - val_accuracy: 0.9317 Epoch 167/500 128/6993 [..............................] - ETA: 0s - loss: 0.0452 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0358 - accuracy: 0.9909 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0731 - accuracy: 0.9868 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0987 - accuracy: 0.9860 3200/6993 [============>.................] - ETA: 0s - loss: 0.1136 - accuracy: 0.9847 3968/6993 [================>.............] - ETA: 0s - loss: 0.1040 - accuracy: 0.9851 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0994 - accuracy: 0.9860 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0913 - accuracy: 0.9860 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1035 - accuracy: 0.9858 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1023 - accuracy: 0.9857 - val_loss: 0.7019 - val_accuracy: 0.9267 Epoch 168/500 128/6993 [..............................] - ETA: 0s - loss: 0.0665 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0722 - accuracy: 0.9893 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0793 - accuracy: 0.9875 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0898 - accuracy: 0.9870 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0804 - accuracy: 0.9880 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0806 - accuracy: 0.9882 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0817 - accuracy: 0.9874 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0770 - accuracy: 0.9875 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0720 - accuracy: 0.9880 - val_loss: 0.6824 - val_accuracy: 0.9297 Epoch 169/500 128/6993 [..............................] - ETA: 0s - loss: 0.0542 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0498 - accuracy: 0.9893 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0616 - accuracy: 0.9877 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0488 - accuracy: 0.9885 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0635 - accuracy: 0.9877 4352/6993 [=================>............] - ETA: 0s - loss: 0.0744 - accuracy: 0.9869 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0804 - accuracy: 0.9859 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0763 - accuracy: 0.9862 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0830 - accuracy: 0.9860 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0826 - accuracy: 0.9857 - val_loss: 0.6243 - val_accuracy: 0.9292 Epoch 170/500 128/6993 [..............................] - ETA: 0s - loss: 0.0108 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0428 - accuracy: 0.9877 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0457 - accuracy: 0.9868 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0403 - accuracy: 0.9883 3328/6993 [=============>................] - ETA: 0s - loss: 0.0401 - accuracy: 0.9877 4224/6993 [=================>............] - ETA: 0s - loss: 0.0558 - accuracy: 0.9872 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0613 - accuracy: 0.9876 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0673 - accuracy: 0.9873 6784/6993 [============================>.] - ETA: 0s - loss: 0.0840 - accuracy: 0.9873 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0830 - accuracy: 0.9874 - val_loss: 0.6636 - val_accuracy: 0.9292 Epoch 171/500 128/6993 [..............................] - ETA: 0s - loss: 0.1658 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0503 - accuracy: 0.9909 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1740 - accuracy: 0.9824 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1548 - accuracy: 0.9835 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1662 - accuracy: 0.9834 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1390 - accuracy: 0.9852 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1231 - accuracy: 0.9857 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1179 - accuracy: 0.9862 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1087 - accuracy: 0.9864 6993/6993 [==============================] - 1s 82us/sample - loss: 0.1044 - accuracy: 0.9864 - val_loss: 0.7206 - val_accuracy: 0.9287 Epoch 172/500 128/6993 [..............................] - ETA: 0s - loss: 0.2616 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.1303 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0853 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0760 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0746 - accuracy: 0.9888 3328/6993 [=============>................] - ETA: 0s - loss: 0.0713 - accuracy: 0.9883 3968/6993 [================>.............] - ETA: 0s - loss: 0.0665 - accuracy: 0.9887 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0644 - accuracy: 0.9894 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0686 - accuracy: 0.9888 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0708 - accuracy: 0.9876 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0677 - accuracy: 0.9876 - val_loss: 0.7921 - val_accuracy: 0.9312 Epoch 173/500 128/6993 [..............................] - ETA: 0s - loss: 0.0170 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0891 - accuracy: 0.9873 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0733 - accuracy: 0.9875 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0949 - accuracy: 0.9867 3200/6993 [============>.................] - ETA: 0s - loss: 0.0880 - accuracy: 0.9872 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0883 - accuracy: 0.9872 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0844 - accuracy: 0.9875 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0913 - accuracy: 0.9869 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0872 - accuracy: 0.9873 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0859 - accuracy: 0.9871 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0853 - accuracy: 0.9868 - val_loss: 0.7129 - val_accuracy: 0.9292 Epoch 174/500 128/6993 [..............................] - ETA: 0s - loss: 0.0967 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.2730 - accuracy: 0.9788 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1554 - accuracy: 0.9838 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1152 - accuracy: 0.9874 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0976 - accuracy: 0.9874 4224/6993 [=================>............] - ETA: 0s - loss: 0.1002 - accuracy: 0.9865 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0858 - accuracy: 0.9879 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0801 - accuracy: 0.9880 6784/6993 [============================>.] - ETA: 0s - loss: 0.0747 - accuracy: 0.9881 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0730 - accuracy: 0.9881 - val_loss: 0.7648 - val_accuracy: 0.9307 Epoch 175/500 128/6993 [..............................] - ETA: 0s - loss: 0.0829 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0998 - accuracy: 0.9854 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0735 - accuracy: 0.9886 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0986 - accuracy: 0.9848 3072/6993 [============>.................] - ETA: 0s - loss: 0.0945 - accuracy: 0.9840 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0875 - accuracy: 0.9836 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0978 - accuracy: 0.9829 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0885 - accuracy: 0.9835 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0817 - accuracy: 0.9850 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0845 - accuracy: 0.9848 - val_loss: 0.6924 - val_accuracy: 0.9307 Epoch 176/500 128/6993 [..............................] - ETA: 0s - loss: 0.0263 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0550 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0754 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0938 - accuracy: 0.9874 3456/6993 [=============>................] - ETA: 0s - loss: 0.0950 - accuracy: 0.9867 4352/6993 [=================>............] - ETA: 0s - loss: 0.1020 - accuracy: 0.9869 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0964 - accuracy: 0.9869 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0882 - accuracy: 0.9871 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0872 - accuracy: 0.9874 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0843 - accuracy: 0.9877 - val_loss: 0.8226 - val_accuracy: 0.9196 Epoch 177/500 128/6993 [..............................] - ETA: 0s - loss: 0.0034 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0440 - accuracy: 0.9902 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0706 - accuracy: 0.9870 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0907 - accuracy: 0.9862 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0818 - accuracy: 0.9865 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0707 - accuracy: 0.9879 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0854 - accuracy: 0.9866 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0873 - accuracy: 0.9869 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0883 - accuracy: 0.9867 - val_loss: 0.6701 - val_accuracy: 0.9292 Epoch 178/500 128/6993 [..............................] - ETA: 0s - loss: 0.0631 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1001 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0725 - accuracy: 0.9883 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0693 - accuracy: 0.9871 3456/6993 [=============>................] - ETA: 0s - loss: 0.0745 - accuracy: 0.9858 4352/6993 [=================>............] - ETA: 0s - loss: 0.0935 - accuracy: 0.9851 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0861 - accuracy: 0.9855 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0843 - accuracy: 0.9857 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0811 - accuracy: 0.9856 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0804 - accuracy: 0.9857 - val_loss: 0.6887 - val_accuracy: 0.9242 Epoch 179/500 128/6993 [..............................] - ETA: 0s - loss: 0.0361 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1601 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0912 - accuracy: 0.9880 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0742 - accuracy: 0.9889 3328/6993 [=============>................] - ETA: 0s - loss: 0.0990 - accuracy: 0.9871 4224/6993 [=================>............] - ETA: 0s - loss: 0.0880 - accuracy: 0.9870 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0892 - accuracy: 0.9875 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0813 - accuracy: 0.9879 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0757 - accuracy: 0.9883 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0732 - accuracy: 0.9887 - val_loss: 0.7673 - val_accuracy: 0.9242 Epoch 180/500 128/6993 [..............................] - ETA: 0s - loss: 0.0625 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0301 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1404 - accuracy: 0.9872 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1109 - accuracy: 0.9888 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0957 - accuracy: 0.9898 3072/6993 [============>.................] - ETA: 0s - loss: 0.0887 - accuracy: 0.9893 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0907 - accuracy: 0.9890 4224/6993 [=================>............] - ETA: 0s - loss: 0.0866 - accuracy: 0.9889 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0889 - accuracy: 0.9877 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0901 - accuracy: 0.9872 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0884 - accuracy: 0.9876 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0840 - accuracy: 0.9880 - val_loss: 0.7997 - val_accuracy: 0.9232 Epoch 181/500 128/6993 [..............................] - ETA: 0s - loss: 0.0036 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0348 - accuracy: 0.9911 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0956 - accuracy: 0.9870 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0835 - accuracy: 0.9890 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0893 - accuracy: 0.9872 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1082 - accuracy: 0.9841 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0989 - accuracy: 0.9850 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0900 - accuracy: 0.9861 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0852 - accuracy: 0.9859 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0859 - accuracy: 0.9862 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0879 - accuracy: 0.9863 - val_loss: 0.7387 - val_accuracy: 0.9257 Epoch 182/500 128/6993 [..............................] - ETA: 0s - loss: 0.0050 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0957 - accuracy: 0.9888 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0860 - accuracy: 0.9870 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0851 - accuracy: 0.9848 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0743 - accuracy: 0.9854 3456/6993 [=============>................] - ETA: 0s - loss: 0.0706 - accuracy: 0.9858 4224/6993 [=================>............] - ETA: 0s - loss: 0.0699 - accuracy: 0.9853 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0661 - accuracy: 0.9860 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0683 - accuracy: 0.9851 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0730 - accuracy: 0.9847 6912/6993 [============================>.] - ETA: 0s - loss: 0.0811 - accuracy: 0.9844 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0832 - accuracy: 0.9841 - val_loss: 0.6682 - val_accuracy: 0.9252 Epoch 183/500 128/6993 [..............................] - ETA: 0s - loss: 0.0449 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0899 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0686 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0851 - accuracy: 0.9873 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0824 - accuracy: 0.9879 3456/6993 [=============>................] - ETA: 0s - loss: 0.0757 - accuracy: 0.9878 4224/6993 [=================>............] - ETA: 0s - loss: 0.0799 - accuracy: 0.9882 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0874 - accuracy: 0.9870 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0836 - accuracy: 0.9877 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0831 - accuracy: 0.9875 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0854 - accuracy: 0.9874 - val_loss: 0.7711 - val_accuracy: 0.9272 Epoch 184/500 128/6993 [..............................] - ETA: 0s - loss: 0.0081 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0592 - accuracy: 0.9902 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1062 - accuracy: 0.9870 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1030 - accuracy: 0.9879 3200/6993 [============>.................] - ETA: 0s - loss: 0.0978 - accuracy: 0.9866 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0879 - accuracy: 0.9875 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0838 - accuracy: 0.9882 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0851 - accuracy: 0.9875 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0971 - accuracy: 0.9872 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1105 - accuracy: 0.9867 6993/6993 [==============================] - 1s 86us/sample - loss: 0.1083 - accuracy: 0.9866 - val_loss: 0.7070 - val_accuracy: 0.9232 Epoch 185/500 128/6993 [..............................] - ETA: 0s - loss: 0.0350 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0568 - accuracy: 0.9883 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0550 - accuracy: 0.9909 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0487 - accuracy: 0.9909 3072/6993 [============>.................] - ETA: 0s - loss: 0.0503 - accuracy: 0.9906 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0715 - accuracy: 0.9888 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0807 - accuracy: 0.9887 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0749 - accuracy: 0.9893 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0756 - accuracy: 0.9894 6784/6993 [============================>.] - ETA: 0s - loss: 0.0827 - accuracy: 0.9891 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0927 - accuracy: 0.9891 - val_loss: 0.7077 - val_accuracy: 0.9292 Epoch 186/500 128/6993 [..............................] - ETA: 0s - loss: 0.0452 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0533 - accuracy: 0.9933 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0326 - accuracy: 0.9946 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0421 - accuracy: 0.9926 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0484 - accuracy: 0.9932 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0506 - accuracy: 0.9919 4224/6993 [=================>............] - ETA: 0s - loss: 0.0502 - accuracy: 0.9910 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0557 - accuracy: 0.9894 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0672 - accuracy: 0.9885 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0662 - accuracy: 0.9881 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0637 - accuracy: 0.9883 - val_loss: 0.8152 - val_accuracy: 0.9282 Epoch 187/500 128/6993 [..............................] - ETA: 0s - loss: 7.3151e-04 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0708 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0557 - accuracy: 0.9908 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0532 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0507 - accuracy: 0.9900 3328/6993 [=============>................] - ETA: 0s - loss: 0.0589 - accuracy: 0.9895 4096/6993 [================>.............] - ETA: 0s - loss: 0.0612 - accuracy: 0.9875 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0643 - accuracy: 0.9867 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0689 - accuracy: 0.9866 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0710 - accuracy: 0.9872 6912/6993 [============================>.] - ETA: 0s - loss: 0.0691 - accuracy: 0.9876 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0689 - accuracy: 0.9874 - val_loss: 0.8402 - val_accuracy: 0.9262 Epoch 188/500 128/6993 [..............................] - ETA: 0s - loss: 0.0115 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0469 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0735 - accuracy: 0.9830 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0660 - accuracy: 0.9839 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0610 - accuracy: 0.9851 3456/6993 [=============>................] - ETA: 0s - loss: 0.0531 - accuracy: 0.9864 4096/6993 [================>.............] - ETA: 0s - loss: 0.0652 - accuracy: 0.9866 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0651 - accuracy: 0.9859 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0656 - accuracy: 0.9866 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0660 - accuracy: 0.9870 6912/6993 [============================>.] - ETA: 0s - loss: 0.0622 - accuracy: 0.9874 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0615 - accuracy: 0.9876 - val_loss: 0.9696 - val_accuracy: 0.9267 Epoch 189/500 128/6993 [..............................] - ETA: 0s - loss: 0.0270 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1324 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1590 - accuracy: 0.9849 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1433 - accuracy: 0.9832 3328/6993 [=============>................] - ETA: 0s - loss: 0.1170 - accuracy: 0.9844 4096/6993 [================>.............] - ETA: 0s - loss: 0.1070 - accuracy: 0.9846 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0952 - accuracy: 0.9852 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0911 - accuracy: 0.9853 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0953 - accuracy: 0.9845 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0911 - accuracy: 0.9847 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0903 - accuracy: 0.9847 - val_loss: 0.8338 - val_accuracy: 0.9287 Epoch 190/500 128/6993 [..............................] - ETA: 0s - loss: 0.0064 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0464 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0483 - accuracy: 0.9880 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0681 - accuracy: 0.9883 3456/6993 [=============>................] - ETA: 0s - loss: 0.0548 - accuracy: 0.9893 4352/6993 [=================>............] - ETA: 0s - loss: 0.0542 - accuracy: 0.9901 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0661 - accuracy: 0.9899 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0660 - accuracy: 0.9899 6912/6993 [============================>.] - ETA: 0s - loss: 0.0717 - accuracy: 0.9893 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0711 - accuracy: 0.9894 - val_loss: 0.7434 - val_accuracy: 0.9267 Epoch 191/500 128/6993 [..............................] - ETA: 0s - loss: 0.0352 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0614 - accuracy: 0.9944 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0499 - accuracy: 0.9934 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0606 - accuracy: 0.9910 3456/6993 [=============>................] - ETA: 0s - loss: 0.0730 - accuracy: 0.9902 4224/6993 [=================>............] - ETA: 0s - loss: 0.0756 - accuracy: 0.9898 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0803 - accuracy: 0.9888 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0807 - accuracy: 0.9888 6784/6993 [============================>.] - ETA: 0s - loss: 0.0853 - accuracy: 0.9884 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0872 - accuracy: 0.9881 - val_loss: 0.8439 - val_accuracy: 0.9287 Epoch 192/500 128/6993 [..............................] - ETA: 0s - loss: 0.0402 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0933 - accuracy: 0.9799 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0817 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0802 - accuracy: 0.9871 3328/6993 [=============>................] - ETA: 0s - loss: 0.0737 - accuracy: 0.9877 4224/6993 [=================>............] - ETA: 0s - loss: 0.0628 - accuracy: 0.9882 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0580 - accuracy: 0.9889 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0580 - accuracy: 0.9877 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0609 - accuracy: 0.9874 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0623 - accuracy: 0.9877 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0615 - accuracy: 0.9877 - val_loss: 0.8966 - val_accuracy: 0.9247 Epoch 193/500 128/6993 [..............................] - ETA: 0s - loss: 0.0355 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0496 - accuracy: 0.9854 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0575 - accuracy: 0.9894 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1067 - accuracy: 0.9892 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0875 - accuracy: 0.9908 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1120 - accuracy: 0.9886 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1109 - accuracy: 0.9882 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1089 - accuracy: 0.9875 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1041 - accuracy: 0.9873 - val_loss: 0.8160 - val_accuracy: 0.9333 Epoch 194/500 128/6993 [..............................] - ETA: 0s - loss: 0.0203 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0424 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0722 - accuracy: 0.9900 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0657 - accuracy: 0.9896 3328/6993 [=============>................] - ETA: 0s - loss: 0.0588 - accuracy: 0.9895 3968/6993 [================>.............] - ETA: 0s - loss: 0.0581 - accuracy: 0.9889 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0630 - accuracy: 0.9876 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0633 - accuracy: 0.9870 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0663 - accuracy: 0.9869 6912/6993 [============================>.] - ETA: 0s - loss: 0.0635 - accuracy: 0.9873 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0633 - accuracy: 0.9873 - val_loss: 0.8753 - val_accuracy: 0.9262 Epoch 195/500 128/6993 [..............................] - ETA: 0s - loss: 0.1766 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0737 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0608 - accuracy: 0.9883 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0569 - accuracy: 0.9891 3456/6993 [=============>................] - ETA: 0s - loss: 0.0699 - accuracy: 0.9873 4352/6993 [=================>............] - ETA: 0s - loss: 0.0739 - accuracy: 0.9874 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0690 - accuracy: 0.9874 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0749 - accuracy: 0.9878 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0708 - accuracy: 0.9881 - val_loss: 0.9291 - val_accuracy: 0.9282 Epoch 196/500 128/6993 [..............................] - ETA: 0s - loss: 0.0043 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0238 - accuracy: 0.9961 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0938 - accuracy: 0.9896 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1079 - accuracy: 0.9885 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1073 - accuracy: 0.9886 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0959 - accuracy: 0.9895 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0830 - accuracy: 0.9903 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0812 - accuracy: 0.9899 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0758 - accuracy: 0.9898 - val_loss: 1.0937 - val_accuracy: 0.9272 Epoch 197/500 128/6993 [..............................] - ETA: 0s - loss: 0.1398 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1069 - accuracy: 0.9854 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1089 - accuracy: 0.9859 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1003 - accuracy: 0.9859 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0906 - accuracy: 0.9869 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0846 - accuracy: 0.9875 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0783 - accuracy: 0.9881 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0770 - accuracy: 0.9882 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0737 - accuracy: 0.9887 - val_loss: 0.8834 - val_accuracy: 0.9317 Epoch 198/500 128/6993 [..............................] - ETA: 0s - loss: 0.0171 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.1172 - accuracy: 0.9909 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0873 - accuracy: 0.9915 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1104 - accuracy: 0.9903 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1012 - accuracy: 0.9908 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1126 - accuracy: 0.9878 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1165 - accuracy: 0.9859 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1258 - accuracy: 0.9860 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1185 - accuracy: 0.9857 6912/6993 [============================>.] - ETA: 0s - loss: 0.1197 - accuracy: 0.9857 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1184 - accuracy: 0.9858 - val_loss: 0.9737 - val_accuracy: 0.9272 Epoch 199/500 128/6993 [..............................] - ETA: 0s - loss: 0.1886 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0889 - accuracy: 0.9922 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1476 - accuracy: 0.9915 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1090 - accuracy: 0.9926 3072/6993 [============>.................] - ETA: 0s - loss: 0.0977 - accuracy: 0.9919 3968/6993 [================>.............] - ETA: 0s - loss: 0.0904 - accuracy: 0.9912 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0970 - accuracy: 0.9903 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1002 - accuracy: 0.9891 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1060 - accuracy: 0.9881 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1016 - accuracy: 0.9886 - val_loss: 0.7278 - val_accuracy: 0.9312 Epoch 200/500 128/6993 [..............................] - ETA: 0s - loss: 0.0119 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0616 - accuracy: 0.9893 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0586 - accuracy: 0.9891 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0557 - accuracy: 0.9897 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0567 - accuracy: 0.9903 4352/6993 [=================>............] - ETA: 0s - loss: 0.0622 - accuracy: 0.9906 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0822 - accuracy: 0.9900 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0743 - accuracy: 0.9906 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0726 - accuracy: 0.9903 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0728 - accuracy: 0.9900 - val_loss: 0.9344 - val_accuracy: 0.9237 Epoch 201/500 128/6993 [..............................] - ETA: 0s - loss: 0.1231 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1097 - accuracy: 0.9824 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1254 - accuracy: 0.9807 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1010 - accuracy: 0.9825 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0940 - accuracy: 0.9852 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0824 - accuracy: 0.9859 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0776 - accuracy: 0.9870 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0712 - accuracy: 0.9877 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0668 - accuracy: 0.9878 - val_loss: 0.8633 - val_accuracy: 0.9287 Epoch 202/500 128/6993 [..............................] - ETA: 0s - loss: 0.0046 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0194 - accuracy: 0.9922 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0231 - accuracy: 0.9928 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0363 - accuracy: 0.9901 3328/6993 [=============>................] - ETA: 0s - loss: 0.0424 - accuracy: 0.9904 4224/6993 [=================>............] - ETA: 0s - loss: 0.0469 - accuracy: 0.9898 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0487 - accuracy: 0.9895 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0552 - accuracy: 0.9887 6912/6993 [============================>.] - ETA: 0s - loss: 0.0550 - accuracy: 0.9887 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0611 - accuracy: 0.9887 - val_loss: 0.9167 - val_accuracy: 0.9252 Epoch 203/500 128/6993 [..............................] - ETA: 0s - loss: 0.0016 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0979 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0702 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0724 - accuracy: 0.9885 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0877 - accuracy: 0.9863 4352/6993 [=================>............] - ETA: 0s - loss: 0.0776 - accuracy: 0.9874 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0745 - accuracy: 0.9876 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0775 - accuracy: 0.9871 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0726 - accuracy: 0.9873 - val_loss: 0.8896 - val_accuracy: 0.9221 Epoch 204/500 128/6993 [..............................] - ETA: 0s - loss: 0.0119 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0663 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0564 - accuracy: 0.9883 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0567 - accuracy: 0.9898 3328/6993 [=============>................] - ETA: 0s - loss: 0.0680 - accuracy: 0.9898 4224/6993 [=================>............] - ETA: 0s - loss: 0.0708 - accuracy: 0.9898 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0687 - accuracy: 0.9906 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0891 - accuracy: 0.9896 6784/6993 [============================>.] - ETA: 0s - loss: 0.0890 - accuracy: 0.9892 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0878 - accuracy: 0.9891 - val_loss: 0.8133 - val_accuracy: 0.9221 Epoch 205/500 128/6993 [..............................] - ETA: 0s - loss: 0.0820 - accuracy: 0.9609 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0956 - accuracy: 0.9854 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0976 - accuracy: 0.9855 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0836 - accuracy: 0.9870 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0684 - accuracy: 0.9880 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0590 - accuracy: 0.9895 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0652 - accuracy: 0.9892 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0636 - accuracy: 0.9893 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0605 - accuracy: 0.9896 - val_loss: 0.8186 - val_accuracy: 0.9343 Epoch 206/500 128/6993 [..............................] - ETA: 0s - loss: 0.0570 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0847 - accuracy: 0.9863 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0715 - accuracy: 0.9905 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0979 - accuracy: 0.9866 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0964 - accuracy: 0.9874 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0867 - accuracy: 0.9886 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0838 - accuracy: 0.9888 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0760 - accuracy: 0.9893 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0847 - accuracy: 0.9894 - val_loss: 0.8905 - val_accuracy: 0.9267 Epoch 207/500 128/6993 [..............................] - ETA: 0s - loss: 0.0047 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0897 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0866 - accuracy: 0.9855 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0848 - accuracy: 0.9870 3456/6993 [=============>................] - ETA: 0s - loss: 0.0969 - accuracy: 0.9870 4352/6993 [=================>............] - ETA: 0s - loss: 0.1104 - accuracy: 0.9871 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1112 - accuracy: 0.9872 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1067 - accuracy: 0.9874 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1089 - accuracy: 0.9872 6993/6993 [==============================] - 1s 82us/sample - loss: 0.1055 - accuracy: 0.9873 - val_loss: 0.8755 - val_accuracy: 0.9272 Epoch 208/500 128/6993 [..............................] - ETA: 0s - loss: 0.0080 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0631 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0732 - accuracy: 0.9838 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0607 - accuracy: 0.9856 3072/6993 [============>.................] - ETA: 0s - loss: 0.0737 - accuracy: 0.9857 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0725 - accuracy: 0.9868 4352/6993 [=================>............] - ETA: 0s - loss: 0.0690 - accuracy: 0.9871 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0742 - accuracy: 0.9878 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0995 - accuracy: 0.9870 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1036 - accuracy: 0.9866 6912/6993 [============================>.] - ETA: 0s - loss: 0.0999 - accuracy: 0.9867 6993/6993 [==============================] - 1s 93us/sample - loss: 0.1001 - accuracy: 0.9866 - val_loss: 0.9145 - val_accuracy: 0.9237 Epoch 209/500 128/6993 [..............................] - ETA: 0s - loss: 0.0034 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0478 - accuracy: 0.9911 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0465 - accuracy: 0.9910 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0505 - accuracy: 0.9897 3200/6993 [============>.................] - ETA: 0s - loss: 0.0900 - accuracy: 0.9881 3968/6993 [================>.............] - ETA: 0s - loss: 0.0768 - accuracy: 0.9899 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0802 - accuracy: 0.9897 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0744 - accuracy: 0.9896 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0722 - accuracy: 0.9901 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0704 - accuracy: 0.9898 - val_loss: 0.7967 - val_accuracy: 0.9307 Epoch 210/500 128/6993 [..............................] - ETA: 0s - loss: 0.0377 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1239 - accuracy: 0.9810 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0758 - accuracy: 0.9872 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0832 - accuracy: 0.9870 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0780 - accuracy: 0.9869 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0788 - accuracy: 0.9873 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1045 - accuracy: 0.9863 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1013 - accuracy: 0.9870 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0999 - accuracy: 0.9870 - val_loss: 0.9585 - val_accuracy: 0.9262 Epoch 211/500 128/6993 [..............................] - ETA: 0s - loss: 0.0422 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0964 - accuracy: 0.9893 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1692 - accuracy: 0.9859 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1387 - accuracy: 0.9869 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1313 - accuracy: 0.9860 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1313 - accuracy: 0.9866 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1210 - accuracy: 0.9866 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1254 - accuracy: 0.9868 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1267 - accuracy: 0.9866 - val_loss: 0.7125 - val_accuracy: 0.9257 Epoch 212/500 128/6993 [..............................] - ETA: 0s - loss: 0.0240 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0544 - accuracy: 0.9873 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0575 - accuracy: 0.9894 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0567 - accuracy: 0.9900 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0534 - accuracy: 0.9916 4352/6993 [=================>............] - ETA: 0s - loss: 0.0741 - accuracy: 0.9892 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0705 - accuracy: 0.9889 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0677 - accuracy: 0.9891 6912/6993 [============================>.] - ETA: 0s - loss: 0.0712 - accuracy: 0.9889 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0732 - accuracy: 0.9888 - val_loss: 0.7869 - val_accuracy: 0.9232 Epoch 213/500 128/6993 [..............................] - ETA: 0s - loss: 0.1209 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0981 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1032 - accuracy: 0.9827 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0854 - accuracy: 0.9832 3456/6993 [=============>................] - ETA: 0s - loss: 0.0807 - accuracy: 0.9858 4224/6993 [=================>............] - ETA: 0s - loss: 0.0902 - accuracy: 0.9863 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0813 - accuracy: 0.9873 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0837 - accuracy: 0.9875 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0784 - accuracy: 0.9881 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0763 - accuracy: 0.9880 - val_loss: 0.7700 - val_accuracy: 0.9242 Epoch 214/500 128/6993 [..............................] - ETA: 0s - loss: 0.1029 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1115 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0878 - accuracy: 0.9860 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0914 - accuracy: 0.9885 3456/6993 [=============>................] - ETA: 0s - loss: 0.0852 - accuracy: 0.9881 4352/6993 [=================>............] - ETA: 0s - loss: 0.0761 - accuracy: 0.9885 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0814 - accuracy: 0.9880 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0733 - accuracy: 0.9891 6912/6993 [============================>.] - ETA: 0s - loss: 0.0750 - accuracy: 0.9881 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0744 - accuracy: 0.9883 - val_loss: 0.8319 - val_accuracy: 0.9232 Epoch 215/500 128/6993 [..............................] - ETA: 0s - loss: 0.0014 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0537 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1049 - accuracy: 0.9832 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0871 - accuracy: 0.9840 3456/6993 [=============>................] - ETA: 0s - loss: 0.0826 - accuracy: 0.9864 4224/6993 [=================>............] - ETA: 0s - loss: 0.0789 - accuracy: 0.9865 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0812 - accuracy: 0.9871 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0991 - accuracy: 0.9861 6784/6993 [============================>.] - ETA: 0s - loss: 0.1001 - accuracy: 0.9856 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0984 - accuracy: 0.9856 - val_loss: 0.8373 - val_accuracy: 0.9282 Epoch 216/500 128/6993 [..............................] - ETA: 0s - loss: 0.0052 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0471 - accuracy: 0.9955 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0510 - accuracy: 0.9894 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0446 - accuracy: 0.9911 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0486 - accuracy: 0.9911 4352/6993 [=================>............] - ETA: 0s - loss: 0.0515 - accuracy: 0.9903 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0554 - accuracy: 0.9889 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0554 - accuracy: 0.9889 6912/6993 [============================>.] - ETA: 0s - loss: 0.0571 - accuracy: 0.9884 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0625 - accuracy: 0.9881 - val_loss: 0.8335 - val_accuracy: 0.9302 Epoch 217/500 128/6993 [..............................] - ETA: 0s - loss: 0.0399 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0811 - accuracy: 0.9810 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0992 - accuracy: 0.9833 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0934 - accuracy: 0.9832 3456/6993 [=============>................] - ETA: 0s - loss: 0.0761 - accuracy: 0.9864 4224/6993 [=================>............] - ETA: 0s - loss: 0.0731 - accuracy: 0.9863 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0715 - accuracy: 0.9869 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0708 - accuracy: 0.9869 6784/6993 [============================>.] - ETA: 0s - loss: 0.0701 - accuracy: 0.9873 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0706 - accuracy: 0.9870 - val_loss: 0.9580 - val_accuracy: 0.9272 Epoch 218/500 128/6993 [..............................] - ETA: 0s - loss: 0.1542 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1181 - accuracy: 0.9818 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0922 - accuracy: 0.9857 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0718 - accuracy: 0.9887 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0652 - accuracy: 0.9901 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0565 - accuracy: 0.9908 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0649 - accuracy: 0.9907 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0657 - accuracy: 0.9907 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0641 - accuracy: 0.9900 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0604 - accuracy: 0.9900 - val_loss: 1.0402 - val_accuracy: 0.9272 Epoch 219/500 128/6993 [..............................] - ETA: 0s - loss: 0.0115 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0744 - accuracy: 0.9873 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0535 - accuracy: 0.9880 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9896 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0595 - accuracy: 0.9902 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0547 - accuracy: 0.9904 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0529 - accuracy: 0.9901 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0595 - accuracy: 0.9894 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0660 - accuracy: 0.9887 - val_loss: 1.0576 - val_accuracy: 0.9262 Epoch 220/500 128/6993 [..............................] - ETA: 0s - loss: 0.6397 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1302 - accuracy: 0.9873 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1132 - accuracy: 0.9891 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1169 - accuracy: 0.9892 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0983 - accuracy: 0.9897 4352/6993 [=================>............] - ETA: 0s - loss: 0.0956 - accuracy: 0.9897 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1122 - accuracy: 0.9901 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1300 - accuracy: 0.9899 6912/6993 [============================>.] - ETA: 0s - loss: 0.1213 - accuracy: 0.9894 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1229 - accuracy: 0.9893 - val_loss: 0.9001 - val_accuracy: 0.9312 Epoch 221/500 128/6993 [..............................] - ETA: 0s - loss: 0.2776 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0658 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0427 - accuracy: 0.9922 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0383 - accuracy: 0.9930 3456/6993 [=============>................] - ETA: 0s - loss: 0.0417 - accuracy: 0.9919 4224/6993 [=================>............] - ETA: 0s - loss: 0.0552 - accuracy: 0.9896 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0775 - accuracy: 0.9881 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0927 - accuracy: 0.9874 6784/6993 [============================>.] - ETA: 0s - loss: 0.0891 - accuracy: 0.9872 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0872 - accuracy: 0.9873 - val_loss: 0.9196 - val_accuracy: 0.9277 Epoch 222/500 128/6993 [..............................] - ETA: 0s - loss: 0.0041 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0561 - accuracy: 0.9893 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0431 - accuracy: 0.9901 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0760 - accuracy: 0.9896 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0895 - accuracy: 0.9900 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0891 - accuracy: 0.9893 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0823 - accuracy: 0.9893 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0923 - accuracy: 0.9886 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0884 - accuracy: 0.9890 - val_loss: 1.0462 - val_accuracy: 0.9232 Epoch 223/500 128/6993 [..............................] - ETA: 0s - loss: 0.0335 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0442 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0565 - accuracy: 0.9844 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0672 - accuracy: 0.9852 3200/6993 [============>.................] - ETA: 0s - loss: 0.0709 - accuracy: 0.9847 3968/6993 [================>.............] - ETA: 0s - loss: 0.0726 - accuracy: 0.9856 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0776 - accuracy: 0.9864 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0735 - accuracy: 0.9872 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0740 - accuracy: 0.9870 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0722 - accuracy: 0.9873 - val_loss: 0.9221 - val_accuracy: 0.9297 Epoch 224/500 128/6993 [..............................] - ETA: 0s - loss: 0.0589 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0285 - accuracy: 0.9941 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0258 - accuracy: 0.9950 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0873 - accuracy: 0.9933 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0817 - accuracy: 0.9927 4352/6993 [=================>............] - ETA: 0s - loss: 0.0766 - accuracy: 0.9922 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0872 - accuracy: 0.9905 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0863 - accuracy: 0.9907 6912/6993 [============================>.] - ETA: 0s - loss: 0.0817 - accuracy: 0.9907 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0812 - accuracy: 0.9907 - val_loss: 1.0153 - val_accuracy: 0.9292 Epoch 225/500 128/6993 [..............................] - ETA: 0s - loss: 0.2274 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0487 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0458 - accuracy: 0.9894 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0525 - accuracy: 0.9887 3456/6993 [=============>................] - ETA: 0s - loss: 0.0545 - accuracy: 0.9884 4352/6993 [=================>............] - ETA: 0s - loss: 0.0822 - accuracy: 0.9885 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0928 - accuracy: 0.9883 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0975 - accuracy: 0.9875 6912/6993 [============================>.] - ETA: 0s - loss: 0.0949 - accuracy: 0.9874 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0938 - accuracy: 0.9876 - val_loss: 1.0687 - val_accuracy: 0.9201 Epoch 226/500 128/6993 [..............................] - ETA: 0s - loss: 0.0174 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0510 - accuracy: 0.9902 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0693 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0818 - accuracy: 0.9907 3456/6993 [=============>................] - ETA: 0s - loss: 0.0823 - accuracy: 0.9896 4352/6993 [=================>............] - ETA: 0s - loss: 0.0736 - accuracy: 0.9885 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0781 - accuracy: 0.9880 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0733 - accuracy: 0.9880 6912/6993 [============================>.] - ETA: 0s - loss: 0.0871 - accuracy: 0.9876 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0862 - accuracy: 0.9877 - val_loss: 0.8803 - val_accuracy: 0.9292 Epoch 227/500 128/6993 [..............................] - ETA: 0s - loss: 0.0077 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.1426 - accuracy: 0.9844 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1184 - accuracy: 0.9844 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0905 - accuracy: 0.9871 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0834 - accuracy: 0.9869 3456/6993 [=============>................] - ETA: 0s - loss: 0.1218 - accuracy: 0.9858 4224/6993 [=================>............] - ETA: 0s - loss: 0.1221 - accuracy: 0.9867 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1148 - accuracy: 0.9866 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1082 - accuracy: 0.9863 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1029 - accuracy: 0.9866 6912/6993 [============================>.] - ETA: 0s - loss: 0.0994 - accuracy: 0.9867 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0987 - accuracy: 0.9866 - val_loss: 0.8624 - val_accuracy: 0.9317 Epoch 228/500 128/6993 [..............................] - ETA: 0s - loss: 0.0637 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1129 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0896 - accuracy: 0.9900 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0753 - accuracy: 0.9892 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0654 - accuracy: 0.9891 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0633 - accuracy: 0.9904 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0618 - accuracy: 0.9904 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0582 - accuracy: 0.9912 6912/6993 [============================>.] - ETA: 0s - loss: 0.0687 - accuracy: 0.9894 6993/6993 [==============================] - 1s 77us/sample - loss: 0.0680 - accuracy: 0.9896 - val_loss: 0.8387 - val_accuracy: 0.9348 Epoch 229/500 128/6993 [..............................] - ETA: 0s - loss: 0.0224 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0338 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0477 - accuracy: 0.9866 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0470 - accuracy: 0.9874 3328/6993 [=============>................] - ETA: 0s - loss: 0.0406 - accuracy: 0.9892 4096/6993 [================>.............] - ETA: 0s - loss: 0.0516 - accuracy: 0.9885 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0603 - accuracy: 0.9890 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0631 - accuracy: 0.9881 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0643 - accuracy: 0.9885 6993/6993 [==============================] - 1s 77us/sample - loss: 0.0651 - accuracy: 0.9883 - val_loss: 0.9729 - val_accuracy: 0.9272 Epoch 230/500 128/6993 [..............................] - ETA: 0s - loss: 0.0076 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0456 - accuracy: 0.9944 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0612 - accuracy: 0.9933 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0583 - accuracy: 0.9914 3072/6993 [============>.................] - ETA: 0s - loss: 0.0611 - accuracy: 0.9919 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0649 - accuracy: 0.9908 4352/6993 [=================>............] - ETA: 0s - loss: 0.0676 - accuracy: 0.9908 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0590 - accuracy: 0.9912 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0565 - accuracy: 0.9914 6784/6993 [============================>.] - ETA: 0s - loss: 0.0636 - accuracy: 0.9909 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0625 - accuracy: 0.9910 - val_loss: 1.1648 - val_accuracy: 0.9247 Epoch 231/500 128/6993 [..............................] - ETA: 0s - loss: 0.1875 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1675 - accuracy: 0.9824 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1562 - accuracy: 0.9849 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1280 - accuracy: 0.9847 3456/6993 [=============>................] - ETA: 0s - loss: 0.1114 - accuracy: 0.9855 4352/6993 [=================>............] - ETA: 0s - loss: 0.1031 - accuracy: 0.9851 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0974 - accuracy: 0.9861 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1042 - accuracy: 0.9855 6912/6993 [============================>.] - ETA: 0s - loss: 0.1010 - accuracy: 0.9867 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1000 - accuracy: 0.9868 - val_loss: 0.9394 - val_accuracy: 0.9287 Epoch 232/500 128/6993 [..............................] - ETA: 0s - loss: 0.0127 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1222 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1085 - accuracy: 0.9883 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0872 - accuracy: 0.9906 3328/6993 [=============>................] - ETA: 0s - loss: 0.1114 - accuracy: 0.9892 4096/6993 [================>.............] - ETA: 0s - loss: 0.0996 - accuracy: 0.9893 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1063 - accuracy: 0.9885 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0982 - accuracy: 0.9893 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0883 - accuracy: 0.9902 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0920 - accuracy: 0.9897 - val_loss: 1.0899 - val_accuracy: 0.9277 Epoch 233/500 128/6993 [..............................] - ETA: 0s - loss: 0.0039 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2306 - accuracy: 0.9893 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1582 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1350 - accuracy: 0.9874 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1177 - accuracy: 0.9869 4352/6993 [=================>............] - ETA: 0s - loss: 0.1094 - accuracy: 0.9871 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0961 - accuracy: 0.9888 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0884 - accuracy: 0.9893 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0844 - accuracy: 0.9896 - val_loss: 0.9142 - val_accuracy: 0.9237 Epoch 234/500 128/6993 [..............................] - ETA: 0s - loss: 0.0426 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0640 - accuracy: 0.9911 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0638 - accuracy: 0.9900 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0707 - accuracy: 0.9885 3072/6993 [============>.................] - ETA: 0s - loss: 0.0768 - accuracy: 0.9880 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1115 - accuracy: 0.9884 4352/6993 [=================>............] - ETA: 0s - loss: 0.0976 - accuracy: 0.9894 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0994 - accuracy: 0.9899 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0929 - accuracy: 0.9898 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0903 - accuracy: 0.9899 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0871 - accuracy: 0.9901 - val_loss: 0.9346 - val_accuracy: 0.9333 Epoch 235/500 128/6993 [..............................] - ETA: 0s - loss: 0.0422 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0895 - accuracy: 0.9900 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1654 - accuracy: 0.9894 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1342 - accuracy: 0.9898 3456/6993 [=============>................] - ETA: 0s - loss: 0.1187 - accuracy: 0.9893 4352/6993 [=================>............] - ETA: 0s - loss: 0.1052 - accuracy: 0.9899 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0995 - accuracy: 0.9902 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1082 - accuracy: 0.9905 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1001 - accuracy: 0.9911 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0949 - accuracy: 0.9913 - val_loss: 0.9868 - val_accuracy: 0.9272 Epoch 236/500 128/6993 [..............................] - ETA: 0s - loss: 0.0283 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0249 - accuracy: 0.9909 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0677 - accuracy: 0.9916 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0687 - accuracy: 0.9914 3456/6993 [=============>................] - ETA: 0s - loss: 0.0650 - accuracy: 0.9907 4352/6993 [=================>............] - ETA: 0s - loss: 0.0715 - accuracy: 0.9903 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0858 - accuracy: 0.9893 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0826 - accuracy: 0.9889 6784/6993 [============================>.] - ETA: 0s - loss: 0.0800 - accuracy: 0.9891 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0785 - accuracy: 0.9891 - val_loss: 0.9430 - val_accuracy: 0.9297 Epoch 237/500 128/6993 [..............................] - ETA: 0s - loss: 0.0036 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0722 - accuracy: 0.9857 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0670 - accuracy: 0.9896 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0631 - accuracy: 0.9899 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0604 - accuracy: 0.9901 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0555 - accuracy: 0.9911 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0852 - accuracy: 0.9901 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0854 - accuracy: 0.9902 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0761 - accuracy: 0.9905 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0737 - accuracy: 0.9906 - val_loss: 0.9402 - val_accuracy: 0.9272 Epoch 238/500 128/6993 [..............................] - ETA: 0s - loss: 0.0300 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0335 - accuracy: 0.9902 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0872 - accuracy: 0.9901 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1061 - accuracy: 0.9886 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1109 - accuracy: 0.9894 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0964 - accuracy: 0.9897 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0867 - accuracy: 0.9905 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0845 - accuracy: 0.9905 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0882 - accuracy: 0.9907 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0868 - accuracy: 0.9904 - val_loss: 1.0473 - val_accuracy: 0.9272 Epoch 239/500 128/6993 [..............................] - ETA: 0s - loss: 0.0148 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0561 - accuracy: 0.9855 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0475 - accuracy: 0.9898 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0571 - accuracy: 0.9900 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0627 - accuracy: 0.9905 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0651 - accuracy: 0.9887 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0734 - accuracy: 0.9878 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1072 - accuracy: 0.9881 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0968 - accuracy: 0.9884 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0949 - accuracy: 0.9881 - val_loss: 0.9057 - val_accuracy: 0.9302 Epoch 240/500 128/6993 [..............................] - ETA: 0s - loss: 0.0057 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.1044 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1262 - accuracy: 0.9850 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1060 - accuracy: 0.9874 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0953 - accuracy: 0.9888 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0870 - accuracy: 0.9894 4224/6993 [=================>............] - ETA: 0s - loss: 0.0767 - accuracy: 0.9905 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0725 - accuracy: 0.9903 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0820 - accuracy: 0.9898 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0776 - accuracy: 0.9900 6912/6993 [============================>.] - ETA: 0s - loss: 0.0789 - accuracy: 0.9900 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0797 - accuracy: 0.9900 - val_loss: 0.9309 - val_accuracy: 0.9262 Epoch 241/500 128/6993 [..............................] - ETA: 0s - loss: 0.0092 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0473 - accuracy: 0.9877 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1094 - accuracy: 0.9868 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1498 - accuracy: 0.9863 3328/6993 [=============>................] - ETA: 0s - loss: 0.1192 - accuracy: 0.9886 3968/6993 [================>.............] - ETA: 0s - loss: 0.1039 - accuracy: 0.9892 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0978 - accuracy: 0.9889 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0999 - accuracy: 0.9895 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1142 - accuracy: 0.9883 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1063 - accuracy: 0.9887 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1019 - accuracy: 0.9888 - val_loss: 0.9400 - val_accuracy: 0.9317 Epoch 242/500 128/6993 [..............................] - ETA: 0s - loss: 0.0019 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0649 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0688 - accuracy: 0.9916 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0644 - accuracy: 0.9901 3200/6993 [============>.................] - ETA: 0s - loss: 0.0730 - accuracy: 0.9891 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0830 - accuracy: 0.9888 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0775 - accuracy: 0.9886 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0764 - accuracy: 0.9884 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0898 - accuracy: 0.9880 6784/6993 [============================>.] - ETA: 0s - loss: 0.0875 - accuracy: 0.9875 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0885 - accuracy: 0.9876 - val_loss: 1.1124 - val_accuracy: 0.9247 Epoch 243/500 128/6993 [..............................] - ETA: 0s - loss: 0.2816 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1098 - accuracy: 0.9854 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1133 - accuracy: 0.9880 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1322 - accuracy: 0.9874 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1080 - accuracy: 0.9877 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1094 - accuracy: 0.9879 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1082 - accuracy: 0.9887 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1079 - accuracy: 0.9884 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1042 - accuracy: 0.9888 - val_loss: 0.8708 - val_accuracy: 0.9378 Epoch 244/500 128/6993 [..............................] - ETA: 0s - loss: 0.0979 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0282 - accuracy: 0.9922 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0686 - accuracy: 0.9896 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1295 - accuracy: 0.9867 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1159 - accuracy: 0.9865 3456/6993 [=============>................] - ETA: 0s - loss: 0.1012 - accuracy: 0.9873 4224/6993 [=================>............] - ETA: 0s - loss: 0.0893 - accuracy: 0.9875 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1021 - accuracy: 0.9874 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0941 - accuracy: 0.9878 6784/6993 [============================>.] - ETA: 0s - loss: 0.0893 - accuracy: 0.9878 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0943 - accuracy: 0.9874 - val_loss: 0.9445 - val_accuracy: 0.9317 Epoch 245/500 128/6993 [..............................] - ETA: 0s - loss: 6.9342e-04 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0142 - accuracy: 0.9948 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0437 - accuracy: 0.9909 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0550 - accuracy: 0.9893 3328/6993 [=============>................] - ETA: 0s - loss: 0.0882 - accuracy: 0.9886 4096/6993 [================>.............] - ETA: 0s - loss: 0.0914 - accuracy: 0.9875 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0822 - accuracy: 0.9884 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0736 - accuracy: 0.9893 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0779 - accuracy: 0.9882 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0845 - accuracy: 0.9876 - val_loss: 0.8084 - val_accuracy: 0.9302 Epoch 246/500 128/6993 [..............................] - ETA: 0s - loss: 0.0165 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0235 - accuracy: 0.9933 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0752 - accuracy: 0.9889 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0595 - accuracy: 0.9905 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0535 - accuracy: 0.9908 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0536 - accuracy: 0.9908 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0598 - accuracy: 0.9891 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0677 - accuracy: 0.9891 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0722 - accuracy: 0.9895 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0748 - accuracy: 0.9896 - val_loss: 0.8490 - val_accuracy: 0.9312 Epoch 247/500 128/6993 [..............................] - ETA: 0s - loss: 0.4586 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2427 - accuracy: 0.9863 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1898 - accuracy: 0.9838 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1447 - accuracy: 0.9863 3456/6993 [=============>................] - ETA: 0s - loss: 0.1424 - accuracy: 0.9864 4096/6993 [================>.............] - ETA: 0s - loss: 0.1505 - accuracy: 0.9878 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1308 - accuracy: 0.9883 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1289 - accuracy: 0.9875 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1189 - accuracy: 0.9880 6784/6993 [============================>.] - ETA: 0s - loss: 0.1229 - accuracy: 0.9882 6993/6993 [==============================] - 1s 84us/sample - loss: 0.1311 - accuracy: 0.9880 - val_loss: 0.8273 - val_accuracy: 0.9302 Epoch 248/500 128/6993 [..............................] - ETA: 0s - loss: 0.0043 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0375 - accuracy: 0.9967 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0494 - accuracy: 0.9946 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0553 - accuracy: 0.9942 3200/6993 [============>.................] - ETA: 0s - loss: 0.0534 - accuracy: 0.9937 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0570 - accuracy: 0.9924 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0526 - accuracy: 0.9929 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0610 - accuracy: 0.9916 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0772 - accuracy: 0.9902 6784/6993 [============================>.] - ETA: 0s - loss: 0.0806 - accuracy: 0.9897 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0797 - accuracy: 0.9898 - val_loss: 0.7870 - val_accuracy: 0.9343 Epoch 249/500 128/6993 [..............................] - ETA: 0s - loss: 0.0195 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0370 - accuracy: 0.9933 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0502 - accuracy: 0.9922 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0455 - accuracy: 0.9905 3328/6993 [=============>................] - ETA: 0s - loss: 0.0484 - accuracy: 0.9895 4096/6993 [================>.............] - ETA: 0s - loss: 0.0439 - accuracy: 0.9895 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0435 - accuracy: 0.9901 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0481 - accuracy: 0.9895 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0501 - accuracy: 0.9900 6993/6993 [==============================] - 1s 77us/sample - loss: 0.0479 - accuracy: 0.9903 - val_loss: 0.8632 - val_accuracy: 0.9383 Epoch 250/500 128/6993 [..............................] - ETA: 0s - loss: 0.3310 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2314 - accuracy: 0.9873 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1844 - accuracy: 0.9849 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1410 - accuracy: 0.9866 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1260 - accuracy: 0.9863 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1263 - accuracy: 0.9864 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1241 - accuracy: 0.9869 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1149 - accuracy: 0.9868 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1215 - accuracy: 0.9864 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1151 - accuracy: 0.9867 - val_loss: 0.8147 - val_accuracy: 0.9353 Epoch 251/500 128/6993 [..............................] - ETA: 0s - loss: 0.1463 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0902 - accuracy: 0.9863 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0922 - accuracy: 0.9877 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0817 - accuracy: 0.9875 3456/6993 [=============>................] - ETA: 0s - loss: 0.0730 - accuracy: 0.9887 4224/6993 [=================>............] - ETA: 0s - loss: 0.0670 - accuracy: 0.9898 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0616 - accuracy: 0.9896 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0623 - accuracy: 0.9896 6784/6993 [============================>.] - ETA: 0s - loss: 0.0585 - accuracy: 0.9900 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0606 - accuracy: 0.9897 - val_loss: 0.8489 - val_accuracy: 0.9343 Epoch 252/500 128/6993 [..............................] - ETA: 0s - loss: 0.0528 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0501 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0348 - accuracy: 0.9915 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0766 - accuracy: 0.9913 3200/6993 [============>.................] - ETA: 0s - loss: 0.0719 - accuracy: 0.9912 4096/6993 [================>.............] - ETA: 0s - loss: 0.0723 - accuracy: 0.9905 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1114 - accuracy: 0.9884 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1073 - accuracy: 0.9889 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0971 - accuracy: 0.9896 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0955 - accuracy: 0.9893 - val_loss: 0.9801 - val_accuracy: 0.9338 Epoch 253/500 128/6993 [..............................] - ETA: 0s - loss: 0.5091 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.1985 - accuracy: 0.9818 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1734 - accuracy: 0.9844 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1369 - accuracy: 0.9849 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1372 - accuracy: 0.9847 3456/6993 [=============>................] - ETA: 0s - loss: 0.1258 - accuracy: 0.9858 4224/6993 [=================>............] - ETA: 0s - loss: 0.1051 - accuracy: 0.9875 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0987 - accuracy: 0.9874 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0874 - accuracy: 0.9885 6784/6993 [============================>.] - ETA: 0s - loss: 0.0805 - accuracy: 0.9894 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0800 - accuracy: 0.9891 - val_loss: 1.0526 - val_accuracy: 0.9333 Epoch 254/500 128/6993 [..............................] - ETA: 0s - loss: 0.0555 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0395 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0679 - accuracy: 0.9894 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0658 - accuracy: 0.9900 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0665 - accuracy: 0.9902 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0855 - accuracy: 0.9895 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0777 - accuracy: 0.9901 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0708 - accuracy: 0.9902 6784/6993 [============================>.] - ETA: 0s - loss: 0.0762 - accuracy: 0.9901 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0820 - accuracy: 0.9900 - val_loss: 1.0238 - val_accuracy: 0.9297 Epoch 255/500 128/6993 [..............................] - ETA: 0s - loss: 0.0653 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0891 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1217 - accuracy: 0.9851 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1119 - accuracy: 0.9863 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0981 - accuracy: 0.9871 3072/6993 [============>.................] - ETA: 0s - loss: 0.0885 - accuracy: 0.9873 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0890 - accuracy: 0.9866 4352/6993 [=================>............] - ETA: 0s - loss: 0.0859 - accuracy: 0.9874 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0766 - accuracy: 0.9886 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0921 - accuracy: 0.9891 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1019 - accuracy: 0.9889 6784/6993 [============================>.] - ETA: 0s - loss: 0.0952 - accuracy: 0.9894 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0933 - accuracy: 0.9893 - val_loss: 1.0498 - val_accuracy: 0.9312 Epoch 256/500 128/6993 [..............................] - ETA: 0s - loss: 0.0105 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0753 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0851 - accuracy: 0.9886 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0631 - accuracy: 0.9918 3072/6993 [============>.................] - ETA: 0s - loss: 0.0520 - accuracy: 0.9919 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0530 - accuracy: 0.9922 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0500 - accuracy: 0.9920 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0604 - accuracy: 0.9907 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0568 - accuracy: 0.9907 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0683 - accuracy: 0.9894 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0683 - accuracy: 0.9897 - val_loss: 1.0488 - val_accuracy: 0.9328 Epoch 257/500 128/6993 [..............................] - ETA: 0s - loss: 0.0133 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0905 - accuracy: 0.9877 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0749 - accuracy: 0.9922 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0704 - accuracy: 0.9902 3456/6993 [=============>................] - ETA: 0s - loss: 0.0654 - accuracy: 0.9902 4224/6993 [=================>............] - ETA: 0s - loss: 0.0838 - accuracy: 0.9889 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0810 - accuracy: 0.9897 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0851 - accuracy: 0.9886 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1050 - accuracy: 0.9876 6912/6993 [============================>.] - ETA: 0s - loss: 0.1047 - accuracy: 0.9878 6993/6993 [==============================] - 1s 82us/sample - loss: 0.1036 - accuracy: 0.9880 - val_loss: 0.9125 - val_accuracy: 0.9333 Epoch 258/500 128/6993 [..............................] - ETA: 0s - loss: 0.0035 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0748 - accuracy: 0.9821 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1122 - accuracy: 0.9860 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1126 - accuracy: 0.9867 3328/6993 [=============>................] - ETA: 0s - loss: 0.0994 - accuracy: 0.9871 4224/6993 [=================>............] - ETA: 0s - loss: 0.0867 - accuracy: 0.9886 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0830 - accuracy: 0.9887 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0771 - accuracy: 0.9884 6912/6993 [============================>.] - ETA: 0s - loss: 0.0805 - accuracy: 0.9886 6993/6993 [==============================] - 1s 77us/sample - loss: 0.0797 - accuracy: 0.9887 - val_loss: 0.9782 - val_accuracy: 0.9292 Epoch 259/500 128/6993 [..............................] - ETA: 0s - loss: 0.0056 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.1260 - accuracy: 0.9810 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1113 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1673 - accuracy: 0.9836 3456/6993 [=============>................] - ETA: 0s - loss: 0.1588 - accuracy: 0.9850 4352/6993 [=================>............] - ETA: 0s - loss: 0.1385 - accuracy: 0.9864 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1405 - accuracy: 0.9870 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1309 - accuracy: 0.9875 6912/6993 [============================>.] - ETA: 0s - loss: 0.1232 - accuracy: 0.9880 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1263 - accuracy: 0.9878 - val_loss: 0.8416 - val_accuracy: 0.9373 Epoch 260/500 128/6993 [..............................] - ETA: 0s - loss: 0.0038 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.1745 - accuracy: 0.9935 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1943 - accuracy: 0.9898 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1990 - accuracy: 0.9868 3200/6993 [============>.................] - ETA: 0s - loss: 0.1580 - accuracy: 0.9875 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1375 - accuracy: 0.9875 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1219 - accuracy: 0.9879 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1307 - accuracy: 0.9873 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1352 - accuracy: 0.9871 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1296 - accuracy: 0.9869 6993/6993 [==============================] - 1s 84us/sample - loss: 0.1293 - accuracy: 0.9868 - val_loss: 0.9577 - val_accuracy: 0.9282 Epoch 261/500 128/6993 [..............................] - ETA: 0s - loss: 0.1928 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1799 - accuracy: 0.9854 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1211 - accuracy: 0.9880 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0989 - accuracy: 0.9881 3200/6993 [============>.................] - ETA: 0s - loss: 0.0855 - accuracy: 0.9897 3968/6993 [================>.............] - ETA: 0s - loss: 0.0896 - accuracy: 0.9904 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0845 - accuracy: 0.9897 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0776 - accuracy: 0.9896 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0947 - accuracy: 0.9885 6912/6993 [============================>.] - ETA: 0s - loss: 0.0900 - accuracy: 0.9887 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0891 - accuracy: 0.9888 - val_loss: 0.8307 - val_accuracy: 0.9353 Epoch 262/500 128/6993 [..............................] - ETA: 0s - loss: 0.0048 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0440 - accuracy: 0.9870 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0572 - accuracy: 0.9886 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0642 - accuracy: 0.9894 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0599 - accuracy: 0.9904 3456/6993 [=============>................] - ETA: 0s - loss: 0.0555 - accuracy: 0.9902 4096/6993 [================>.............] - ETA: 0s - loss: 0.0576 - accuracy: 0.9900 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0541 - accuracy: 0.9905 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0703 - accuracy: 0.9900 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0681 - accuracy: 0.9902 6912/6993 [============================>.] - ETA: 0s - loss: 0.0655 - accuracy: 0.9905 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0649 - accuracy: 0.9904 - val_loss: 0.9908 - val_accuracy: 0.9348 Epoch 263/500 128/6993 [..............................] - ETA: 0s - loss: 0.1612 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1004 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1295 - accuracy: 0.9880 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1571 - accuracy: 0.9877 3200/6993 [============>.................] - ETA: 0s - loss: 0.1333 - accuracy: 0.9894 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1149 - accuracy: 0.9906 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1013 - accuracy: 0.9913 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0987 - accuracy: 0.9908 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0939 - accuracy: 0.9908 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0929 - accuracy: 0.9902 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0909 - accuracy: 0.9898 - val_loss: 1.1286 - val_accuracy: 0.9287 Epoch 264/500 128/6993 [..............................] - ETA: 0s - loss: 0.0108 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1066 - accuracy: 0.9893 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0883 - accuracy: 0.9896 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0729 - accuracy: 0.9911 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1059 - accuracy: 0.9900 4224/6993 [=================>............] - ETA: 0s - loss: 0.1053 - accuracy: 0.9901 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0996 - accuracy: 0.9896 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0916 - accuracy: 0.9901 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0914 - accuracy: 0.9898 6784/6993 [============================>.] - ETA: 0s - loss: 0.0958 - accuracy: 0.9904 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0961 - accuracy: 0.9903 - val_loss: 1.3084 - val_accuracy: 0.9201 Epoch 265/500 128/6993 [..............................] - ETA: 0s - loss: 0.0155 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.1343 - accuracy: 0.9875 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0829 - accuracy: 0.9905 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0682 - accuracy: 0.9900 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1760 - accuracy: 0.9873 3072/6993 [============>.................] - ETA: 0s - loss: 0.1491 - accuracy: 0.9889 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1314 - accuracy: 0.9898 4352/6993 [=================>............] - ETA: 0s - loss: 0.1170 - accuracy: 0.9901 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1377 - accuracy: 0.9895 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1236 - accuracy: 0.9895 6912/6993 [============================>.] - ETA: 0s - loss: 0.1113 - accuracy: 0.9894 6993/6993 [==============================] - 1s 88us/sample - loss: 0.1108 - accuracy: 0.9894 - val_loss: 1.1538 - val_accuracy: 0.9272 Epoch 266/500 128/6993 [..............................] - ETA: 0s - loss: 0.0042 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1617 - accuracy: 0.9902 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0957 - accuracy: 0.9896 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0787 - accuracy: 0.9896 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0686 - accuracy: 0.9911 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0630 - accuracy: 0.9908 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0618 - accuracy: 0.9909 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0860 - accuracy: 0.9904 6912/6993 [============================>.] - ETA: 0s - loss: 0.0815 - accuracy: 0.9900 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0806 - accuracy: 0.9901 - val_loss: 1.2468 - val_accuracy: 0.9267 Epoch 267/500 128/6993 [..............................] - ETA: 0s - loss: 0.1595 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1172 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1060 - accuracy: 0.9860 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0938 - accuracy: 0.9871 3328/6993 [=============>................] - ETA: 0s - loss: 0.0921 - accuracy: 0.9871 3968/6993 [================>.............] - ETA: 0s - loss: 0.0921 - accuracy: 0.9866 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0952 - accuracy: 0.9863 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0876 - accuracy: 0.9870 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0985 - accuracy: 0.9872 6784/6993 [============================>.] - ETA: 0s - loss: 0.0927 - accuracy: 0.9879 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0926 - accuracy: 0.9880 - val_loss: 1.1572 - val_accuracy: 0.9237 Epoch 268/500 128/6993 [..............................] - ETA: 0s - loss: 0.0195 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0865 - accuracy: 0.9877 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0875 - accuracy: 0.9896 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0913 - accuracy: 0.9891 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1278 - accuracy: 0.9895 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1181 - accuracy: 0.9892 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1141 - accuracy: 0.9888 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1095 - accuracy: 0.9885 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0979 - accuracy: 0.9887 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0990 - accuracy: 0.9888 - val_loss: 1.0846 - val_accuracy: 0.9216 Epoch 269/500 128/6993 [..............................] - ETA: 0s - loss: 0.0023 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.1423 - accuracy: 0.9877 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1250 - accuracy: 0.9896 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1253 - accuracy: 0.9870 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1250 - accuracy: 0.9864 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1059 - accuracy: 0.9874 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1212 - accuracy: 0.9864 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1165 - accuracy: 0.9857 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1159 - accuracy: 0.9863 6912/6993 [============================>.] - ETA: 0s - loss: 0.1045 - accuracy: 0.9873 6993/6993 [==============================] - 1s 88us/sample - loss: 0.1043 - accuracy: 0.9873 - val_loss: 0.9862 - val_accuracy: 0.9302 Epoch 270/500 128/6993 [..............................] - ETA: 0s - loss: 0.1817 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1146 - accuracy: 0.9873 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1148 - accuracy: 0.9859 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1051 - accuracy: 0.9879 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1161 - accuracy: 0.9883 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1038 - accuracy: 0.9875 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0973 - accuracy: 0.9874 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0941 - accuracy: 0.9869 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0935 - accuracy: 0.9871 - val_loss: 1.1065 - val_accuracy: 0.9302 Epoch 271/500 128/6993 [..............................] - ETA: 0s - loss: 0.0075 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0441 - accuracy: 0.9902 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0319 - accuracy: 0.9922 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0249 - accuracy: 0.9940 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0400 - accuracy: 0.9933 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0526 - accuracy: 0.9924 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0587 - accuracy: 0.9914 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0856 - accuracy: 0.9901 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0791 - accuracy: 0.9903 - val_loss: 1.1531 - val_accuracy: 0.9232 Epoch 272/500 128/6993 [..............................] - ETA: 0s - loss: 0.0547 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1231 - accuracy: 0.9854 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0918 - accuracy: 0.9880 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1153 - accuracy: 0.9862 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1098 - accuracy: 0.9877 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1140 - accuracy: 0.9868 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1089 - accuracy: 0.9867 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1041 - accuracy: 0.9868 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1095 - accuracy: 0.9874 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1053 - accuracy: 0.9876 - val_loss: 0.8930 - val_accuracy: 0.9353 Epoch 273/500 128/6993 [..............................] - ETA: 0s - loss: 0.0750 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0306 - accuracy: 0.9902 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0572 - accuracy: 0.9911 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0799 - accuracy: 0.9881 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0697 - accuracy: 0.9894 4224/6993 [=================>............] - ETA: 0s - loss: 0.0708 - accuracy: 0.9891 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0667 - accuracy: 0.9891 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0652 - accuracy: 0.9893 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0672 - accuracy: 0.9892 6912/6993 [============================>.] - ETA: 0s - loss: 0.0644 - accuracy: 0.9896 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0760 - accuracy: 0.9896 - val_loss: 1.1168 - val_accuracy: 0.9232 Epoch 274/500 128/6993 [..............................] - ETA: 0s - loss: 0.1962 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1408 - accuracy: 0.9873 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1214 - accuracy: 0.9885 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1010 - accuracy: 0.9874 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0906 - accuracy: 0.9869 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0860 - accuracy: 0.9875 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0962 - accuracy: 0.9877 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0900 - accuracy: 0.9872 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0855 - accuracy: 0.9878 - val_loss: 1.0663 - val_accuracy: 0.9317 Epoch 275/500 128/6993 [..............................] - ETA: 0s - loss: 0.0067 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.1284 - accuracy: 0.9911 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0979 - accuracy: 0.9900 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1378 - accuracy: 0.9896 3456/6993 [=============>................] - ETA: 0s - loss: 0.1260 - accuracy: 0.9899 4352/6993 [=================>............] - ETA: 0s - loss: 0.1078 - accuracy: 0.9906 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1089 - accuracy: 0.9905 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1034 - accuracy: 0.9904 6784/6993 [============================>.] - ETA: 0s - loss: 0.1041 - accuracy: 0.9900 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1019 - accuracy: 0.9898 - val_loss: 1.2008 - val_accuracy: 0.9221 Epoch 276/500 128/6993 [..............................] - ETA: 0s - loss: 0.0377 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0392 - accuracy: 0.9922 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0593 - accuracy: 0.9915 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0483 - accuracy: 0.9917 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0520 - accuracy: 0.9922 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0543 - accuracy: 0.9916 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0577 - accuracy: 0.9902 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0611 - accuracy: 0.9903 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0598 - accuracy: 0.9900 6912/6993 [============================>.] - ETA: 0s - loss: 0.0592 - accuracy: 0.9900 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0585 - accuracy: 0.9901 - val_loss: 1.0372 - val_accuracy: 0.9333 Epoch 277/500 128/6993 [..............................] - ETA: 0s - loss: 0.0509 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0859 - accuracy: 0.9922 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0941 - accuracy: 0.9910 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0721 - accuracy: 0.9918 3072/6993 [============>.................] - ETA: 0s - loss: 0.0849 - accuracy: 0.9912 3968/6993 [================>.............] - ETA: 0s - loss: 0.0775 - accuracy: 0.9914 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0855 - accuracy: 0.9903 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0886 - accuracy: 0.9897 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0802 - accuracy: 0.9900 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0812 - accuracy: 0.9900 - val_loss: 1.1149 - val_accuracy: 0.9297 Epoch 278/500 128/6993 [..............................] - ETA: 0s - loss: 0.1772 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0314 - accuracy: 0.9967 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0332 - accuracy: 0.9941 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0519 - accuracy: 0.9939 3072/6993 [============>.................] - ETA: 0s - loss: 0.0467 - accuracy: 0.9932 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0460 - accuracy: 0.9924 4352/6993 [=================>............] - ETA: 0s - loss: 0.0460 - accuracy: 0.9922 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0437 - accuracy: 0.9924 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0414 - accuracy: 0.9924 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0551 - accuracy: 0.9920 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0596 - accuracy: 0.9917 - val_loss: 1.1691 - val_accuracy: 0.9287 Epoch 279/500 128/6993 [..............................] - ETA: 0s - loss: 0.0850 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0955 - accuracy: 0.9933 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1076 - accuracy: 0.9910 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0789 - accuracy: 0.9914 3456/6993 [=============>................] - ETA: 0s - loss: 0.0913 - accuracy: 0.9890 4096/6993 [================>.............] - ETA: 0s - loss: 0.0963 - accuracy: 0.9888 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0949 - accuracy: 0.9890 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0914 - accuracy: 0.9890 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0952 - accuracy: 0.9891 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0902 - accuracy: 0.9896 - val_loss: 1.0791 - val_accuracy: 0.9363 Epoch 280/500 128/6993 [..............................] - ETA: 0s - loss: 6.1247e-04 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0244 - accuracy: 0.9933 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0179 - accuracy: 0.9944 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0324 - accuracy: 0.9949 3456/6993 [=============>................] - ETA: 0s - loss: 0.0414 - accuracy: 0.9933 4352/6993 [=================>............] - ETA: 0s - loss: 0.0458 - accuracy: 0.9924 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0551 - accuracy: 0.9916 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0603 - accuracy: 0.9915 6912/6993 [============================>.] - ETA: 0s - loss: 0.0556 - accuracy: 0.9919 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0550 - accuracy: 0.9920 - val_loss: 1.2362 - val_accuracy: 0.9292 Epoch 281/500 128/6993 [..............................] - ETA: 0s - loss: 0.0344 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0192 - accuracy: 0.9944 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0289 - accuracy: 0.9961 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0486 - accuracy: 0.9926 3456/6993 [=============>................] - ETA: 0s - loss: 0.0438 - accuracy: 0.9931 4352/6993 [=================>............] - ETA: 0s - loss: 0.0548 - accuracy: 0.9929 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0522 - accuracy: 0.9926 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0929 - accuracy: 0.9919 6912/6993 [============================>.] - ETA: 0s - loss: 0.0959 - accuracy: 0.9913 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0988 - accuracy: 0.9908 - val_loss: 1.1858 - val_accuracy: 0.9257 Epoch 282/500 128/6993 [..............................] - ETA: 0s - loss: 0.0798 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1046 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0898 - accuracy: 0.9888 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0790 - accuracy: 0.9883 3456/6993 [=============>................] - ETA: 0s - loss: 0.0800 - accuracy: 0.9873 4224/6993 [=================>............] - ETA: 0s - loss: 0.0960 - accuracy: 0.9860 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0953 - accuracy: 0.9860 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0930 - accuracy: 0.9868 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0898 - accuracy: 0.9867 6912/6993 [============================>.] - ETA: 0s - loss: 0.0841 - accuracy: 0.9874 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0840 - accuracy: 0.9874 - val_loss: 1.2440 - val_accuracy: 0.9277 Epoch 283/500 128/6993 [..............................] - ETA: 0s - loss: 0.2144 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.0935 - accuracy: 0.9891 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0619 - accuracy: 0.9914 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0660 - accuracy: 0.9897 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0705 - accuracy: 0.9890 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0711 - accuracy: 0.9887 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0969 - accuracy: 0.9886 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0895 - accuracy: 0.9888 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0907 - accuracy: 0.9894 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0845 - accuracy: 0.9896 - val_loss: 1.0623 - val_accuracy: 0.9328 Epoch 284/500 128/6993 [..............................] - ETA: 1s - loss: 0.0132 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0992 - accuracy: 0.9911 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0784 - accuracy: 0.9927 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0976 - accuracy: 0.9906 3456/6993 [=============>................] - ETA: 0s - loss: 0.0861 - accuracy: 0.9907 4352/6993 [=================>............] - ETA: 0s - loss: 0.0742 - accuracy: 0.9906 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0734 - accuracy: 0.9910 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0738 - accuracy: 0.9902 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0800 - accuracy: 0.9897 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0847 - accuracy: 0.9887 - val_loss: 1.3530 - val_accuracy: 0.9272 Epoch 285/500 128/6993 [..............................] - ETA: 0s - loss: 0.0285 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0342 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0251 - accuracy: 0.9908 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0483 - accuracy: 0.9893 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0623 - accuracy: 0.9892 3328/6993 [=============>................] - ETA: 0s - loss: 0.0608 - accuracy: 0.9898 3968/6993 [================>.............] - ETA: 0s - loss: 0.0603 - accuracy: 0.9902 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0569 - accuracy: 0.9903 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0588 - accuracy: 0.9901 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0606 - accuracy: 0.9900 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0559 - accuracy: 0.9905 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0554 - accuracy: 0.9907 - val_loss: 1.1994 - val_accuracy: 0.9277 Epoch 286/500 128/6993 [..............................] - ETA: 0s - loss: 0.0167 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1200 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1870 - accuracy: 0.9856 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1670 - accuracy: 0.9879 3200/6993 [============>.................] - ETA: 0s - loss: 0.1438 - accuracy: 0.9894 4096/6993 [================>.............] - ETA: 0s - loss: 0.1260 - accuracy: 0.9897 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1121 - accuracy: 0.9908 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1064 - accuracy: 0.9903 6784/6993 [============================>.] - ETA: 0s - loss: 0.1000 - accuracy: 0.9904 6993/6993 [==============================] - 1s 76us/sample - loss: 0.1114 - accuracy: 0.9894 - val_loss: 1.1185 - val_accuracy: 0.9221 Epoch 287/500 128/6993 [..............................] - ETA: 0s - loss: 0.1704 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0851 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0885 - accuracy: 0.9877 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0741 - accuracy: 0.9891 3328/6993 [=============>................] - ETA: 0s - loss: 0.0641 - accuracy: 0.9898 3968/6993 [================>.............] - ETA: 0s - loss: 0.0798 - accuracy: 0.9902 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0737 - accuracy: 0.9897 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0779 - accuracy: 0.9900 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0793 - accuracy: 0.9895 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0773 - accuracy: 0.9897 - val_loss: 1.2231 - val_accuracy: 0.9267 Epoch 288/500 128/6993 [..............................] - ETA: 0s - loss: 0.0300 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0365 - accuracy: 0.9870 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1600 - accuracy: 0.9886 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1175 - accuracy: 0.9890 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1196 - accuracy: 0.9883 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1007 - accuracy: 0.9891 4224/6993 [=================>............] - ETA: 0s - loss: 0.1017 - accuracy: 0.9893 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0907 - accuracy: 0.9898 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0905 - accuracy: 0.9907 6784/6993 [============================>.] - ETA: 0s - loss: 0.0965 - accuracy: 0.9903 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0973 - accuracy: 0.9903 - val_loss: 1.2721 - val_accuracy: 0.9237 Epoch 289/500 128/6993 [..............................] - ETA: 0s - loss: 0.0091 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.1624 - accuracy: 0.9944 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1179 - accuracy: 0.9922 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1140 - accuracy: 0.9891 3456/6993 [=============>................] - ETA: 0s - loss: 0.1619 - accuracy: 0.9887 4352/6993 [=================>............] - ETA: 0s - loss: 0.1427 - accuracy: 0.9885 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1396 - accuracy: 0.9876 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1428 - accuracy: 0.9864 6912/6993 [============================>.] - ETA: 0s - loss: 0.1604 - accuracy: 0.9855 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1591 - accuracy: 0.9856 - val_loss: 0.9968 - val_accuracy: 0.9292 Epoch 290/500 128/6993 [..............................] - ETA: 0s - loss: 0.3078 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1512 - accuracy: 0.9883 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0979 - accuracy: 0.9900 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1030 - accuracy: 0.9903 3456/6993 [=============>................] - ETA: 0s - loss: 0.1081 - accuracy: 0.9890 4352/6993 [=================>............] - ETA: 0s - loss: 0.1068 - accuracy: 0.9887 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0969 - accuracy: 0.9883 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0983 - accuracy: 0.9885 6912/6993 [============================>.] - ETA: 0s - loss: 0.1022 - accuracy: 0.9886 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1016 - accuracy: 0.9886 - val_loss: 1.0796 - val_accuracy: 0.9267 Epoch 291/500 128/6993 [..............................] - ETA: 0s - loss: 0.0073 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0121 - accuracy: 0.9971 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0486 - accuracy: 0.9911 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0413 - accuracy: 0.9922 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0385 - accuracy: 0.9922 4352/6993 [=================>............] - ETA: 0s - loss: 0.0493 - accuracy: 0.9922 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0536 - accuracy: 0.9922 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0570 - accuracy: 0.9922 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0613 - accuracy: 0.9918 - val_loss: 1.0727 - val_accuracy: 0.9333 Epoch 292/500 128/6993 [..............................] - ETA: 0s - loss: 0.0334 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1417 - accuracy: 0.9870 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1411 - accuracy: 0.9863 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1117 - accuracy: 0.9881 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1092 - accuracy: 0.9883 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0970 - accuracy: 0.9880 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0841 - accuracy: 0.9891 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0949 - accuracy: 0.9888 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0911 - accuracy: 0.9893 6993/6993 [==============================] - 1s 87us/sample - loss: 0.1018 - accuracy: 0.9877 - val_loss: 1.0638 - val_accuracy: 0.9302 Epoch 293/500 128/6993 [..............................] - ETA: 0s - loss: 0.0523 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0247 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0464 - accuracy: 0.9880 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0682 - accuracy: 0.9898 3456/6993 [=============>................] - ETA: 0s - loss: 0.0701 - accuracy: 0.9893 4352/6993 [=================>............] - ETA: 0s - loss: 0.0759 - accuracy: 0.9885 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0774 - accuracy: 0.9884 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0767 - accuracy: 0.9880 6912/6993 [============================>.] - ETA: 0s - loss: 0.0740 - accuracy: 0.9881 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0733 - accuracy: 0.9883 - val_loss: 0.9681 - val_accuracy: 0.9312 Epoch 294/500 128/6993 [..............................] - ETA: 0s - loss: 0.0306 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0721 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0704 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0613 - accuracy: 0.9900 3328/6993 [=============>................] - ETA: 0s - loss: 0.0708 - accuracy: 0.9886 4224/6993 [=================>............] - ETA: 0s - loss: 0.0807 - accuracy: 0.9893 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0870 - accuracy: 0.9894 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0887 - accuracy: 0.9896 6784/6993 [============================>.] - ETA: 0s - loss: 0.0856 - accuracy: 0.9897 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0841 - accuracy: 0.9896 - val_loss: 1.1093 - val_accuracy: 0.9237 Epoch 295/500 128/6993 [..............................] - ETA: 0s - loss: 0.2495 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0567 - accuracy: 0.9900 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0507 - accuracy: 0.9911 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0803 - accuracy: 0.9879 3328/6993 [=============>................] - ETA: 0s - loss: 0.0739 - accuracy: 0.9880 4224/6993 [=================>............] - ETA: 0s - loss: 0.0750 - accuracy: 0.9889 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0819 - accuracy: 0.9882 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0839 - accuracy: 0.9882 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0889 - accuracy: 0.9881 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0913 - accuracy: 0.9880 - val_loss: 0.8705 - val_accuracy: 0.9353 Epoch 296/500 128/6993 [..............................] - ETA: 0s - loss: 0.0752 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0443 - accuracy: 0.9877 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0604 - accuracy: 0.9876 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0635 - accuracy: 0.9883 3072/6993 [============>.................] - ETA: 0s - loss: 0.0644 - accuracy: 0.9870 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0585 - accuracy: 0.9883 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0620 - accuracy: 0.9873 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0705 - accuracy: 0.9868 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0692 - accuracy: 0.9869 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0683 - accuracy: 0.9878 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0650 - accuracy: 0.9883 6993/6993 [==============================] - 1s 97us/sample - loss: 0.0688 - accuracy: 0.9883 - val_loss: 0.9912 - val_accuracy: 0.9307 Epoch 297/500 128/6993 [..............................] - ETA: 0s - loss: 0.0181 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0287 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0396 - accuracy: 0.9915 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0930 - accuracy: 0.9863 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0966 - accuracy: 0.9870 3328/6993 [=============>................] - ETA: 0s - loss: 0.1092 - accuracy: 0.9877 4096/6993 [================>.............] - ETA: 0s - loss: 0.0960 - accuracy: 0.9883 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0833 - accuracy: 0.9895 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0891 - accuracy: 0.9886 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0995 - accuracy: 0.9877 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0919 - accuracy: 0.9883 - val_loss: 0.9395 - val_accuracy: 0.9312 Epoch 298/500 128/6993 [..............................] - ETA: 0s - loss: 0.0183 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.2792 - accuracy: 0.9831 1664/6993 [======>.......................] - ETA: 0s - loss: 0.2218 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1951 - accuracy: 0.9855 3328/6993 [=============>................] - ETA: 0s - loss: 0.1603 - accuracy: 0.9865 4224/6993 [=================>............] - ETA: 0s - loss: 0.1318 - accuracy: 0.9884 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1201 - accuracy: 0.9889 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1205 - accuracy: 0.9887 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1202 - accuracy: 0.9883 6993/6993 [==============================] - 1s 79us/sample - loss: 0.1180 - accuracy: 0.9883 - val_loss: 1.3850 - val_accuracy: 0.9242 Epoch 299/500 128/6993 [..............................] - ETA: 0s - loss: 0.3419 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.2575 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1867 - accuracy: 0.9855 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1902 - accuracy: 0.9851 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1772 - accuracy: 0.9841 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1536 - accuracy: 0.9848 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1392 - accuracy: 0.9855 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1384 - accuracy: 0.9847 6993/6993 [==============================] - 1s 77us/sample - loss: 0.1363 - accuracy: 0.9848 - val_loss: 1.0944 - val_accuracy: 0.9312 Epoch 300/500 128/6993 [..............................] - ETA: 0s - loss: 0.3474 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.1138 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0975 - accuracy: 0.9886 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0933 - accuracy: 0.9895 3456/6993 [=============>................] - ETA: 0s - loss: 0.0822 - accuracy: 0.9890 4352/6993 [=================>............] - ETA: 0s - loss: 0.0705 - accuracy: 0.9901 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0832 - accuracy: 0.9901 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0790 - accuracy: 0.9900 6912/6993 [============================>.] - ETA: 0s - loss: 0.0766 - accuracy: 0.9897 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0758 - accuracy: 0.9898 - val_loss: 1.1236 - val_accuracy: 0.9257 Epoch 301/500 128/6993 [..............................] - ETA: 0s - loss: 0.0031 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0324 - accuracy: 0.9944 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0485 - accuracy: 0.9946 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0497 - accuracy: 0.9918 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0507 - accuracy: 0.9912 3456/6993 [=============>................] - ETA: 0s - loss: 0.0714 - accuracy: 0.9896 4096/6993 [================>.............] - ETA: 0s - loss: 0.0781 - accuracy: 0.9897 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0775 - accuracy: 0.9897 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0796 - accuracy: 0.9898 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0834 - accuracy: 0.9893 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0784 - accuracy: 0.9894 6912/6993 [============================>.] - ETA: 0s - loss: 0.0773 - accuracy: 0.9899 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0767 - accuracy: 0.9898 - val_loss: 1.0620 - val_accuracy: 0.9302 Epoch 302/500 128/6993 [..............................] - ETA: 0s - loss: 0.0116 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0353 - accuracy: 0.9877 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0957 - accuracy: 0.9876 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1460 - accuracy: 0.9860 3328/6993 [=============>................] - ETA: 0s - loss: 0.1342 - accuracy: 0.9856 4224/6993 [=================>............] - ETA: 0s - loss: 0.1197 - accuracy: 0.9872 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1107 - accuracy: 0.9876 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1084 - accuracy: 0.9876 6784/6993 [============================>.] - ETA: 0s - loss: 0.1049 - accuracy: 0.9882 6993/6993 [==============================] - 1s 77us/sample - loss: 0.1041 - accuracy: 0.9884 - val_loss: 1.2181 - val_accuracy: 0.9282 Epoch 303/500 128/6993 [..............................] - ETA: 0s - loss: 0.0038 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0820 - accuracy: 0.9900 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1732 - accuracy: 0.9849 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1405 - accuracy: 0.9868 3072/6993 [============>.................] - ETA: 0s - loss: 0.1395 - accuracy: 0.9863 3968/6993 [================>.............] - ETA: 0s - loss: 0.1179 - accuracy: 0.9877 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1069 - accuracy: 0.9887 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1014 - accuracy: 0.9887 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0935 - accuracy: 0.9893 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0909 - accuracy: 0.9896 - val_loss: 1.0869 - val_accuracy: 0.9338 Epoch 304/500 128/6993 [..............................] - ETA: 0s - loss: 0.0242 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0490 - accuracy: 0.9912 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0406 - accuracy: 0.9932 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0872 - accuracy: 0.9937 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0848 - accuracy: 0.9930 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0883 - accuracy: 0.9929 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0873 - accuracy: 0.9918 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0852 - accuracy: 0.9917 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0841 - accuracy: 0.9916 - val_loss: 1.1505 - val_accuracy: 0.9272 Epoch 305/500 128/6993 [..............................] - ETA: 0s - loss: 0.2244 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0886 - accuracy: 0.9922 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0782 - accuracy: 0.9910 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0643 - accuracy: 0.9908 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0564 - accuracy: 0.9922 3200/6993 [============>.................] - ETA: 0s - loss: 0.0505 - accuracy: 0.9925 3968/6993 [================>.............] - ETA: 0s - loss: 0.1119 - accuracy: 0.9912 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0992 - accuracy: 0.9913 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0920 - accuracy: 0.9918 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1024 - accuracy: 0.9916 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0977 - accuracy: 0.9914 - val_loss: 1.1088 - val_accuracy: 0.9292 Epoch 306/500 128/6993 [..............................] - ETA: 0s - loss: 0.0108 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0414 - accuracy: 0.9909 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0360 - accuracy: 0.9935 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0815 - accuracy: 0.9926 3200/6993 [============>.................] - ETA: 0s - loss: 0.1073 - accuracy: 0.9916 4096/6993 [================>.............] - ETA: 0s - loss: 0.0874 - accuracy: 0.9915 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0883 - accuracy: 0.9918 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0811 - accuracy: 0.9918 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0830 - accuracy: 0.9910 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0802 - accuracy: 0.9911 - val_loss: 1.1510 - val_accuracy: 0.9297 Epoch 307/500 128/6993 [..............................] - ETA: 0s - loss: 0.0251 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0737 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1072 - accuracy: 0.9888 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1134 - accuracy: 0.9877 3328/6993 [=============>................] - ETA: 0s - loss: 0.1049 - accuracy: 0.9874 4224/6993 [=================>............] - ETA: 0s - loss: 0.1015 - accuracy: 0.9884 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0879 - accuracy: 0.9889 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0869 - accuracy: 0.9889 6784/6993 [============================>.] - ETA: 0s - loss: 0.0885 - accuracy: 0.9888 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0864 - accuracy: 0.9890 - val_loss: 1.1718 - val_accuracy: 0.9287 Epoch 308/500 128/6993 [..............................] - ETA: 0s - loss: 0.0039 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0096 - accuracy: 0.9971 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1123 - accuracy: 0.9906 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0991 - accuracy: 0.9915 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0919 - accuracy: 0.9905 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0808 - accuracy: 0.9902 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0961 - accuracy: 0.9890 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0939 - accuracy: 0.9888 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0882 - accuracy: 0.9887 - val_loss: 0.9879 - val_accuracy: 0.9302 Epoch 309/500 128/6993 [..............................] - ETA: 0s - loss: 0.0870 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1317 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0964 - accuracy: 0.9927 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0957 - accuracy: 0.9914 3456/6993 [=============>................] - ETA: 0s - loss: 0.0887 - accuracy: 0.9913 4352/6993 [=================>............] - ETA: 0s - loss: 0.0846 - accuracy: 0.9913 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0777 - accuracy: 0.9916 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0869 - accuracy: 0.9910 6784/6993 [============================>.] - ETA: 0s - loss: 0.0841 - accuracy: 0.9906 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0874 - accuracy: 0.9901 - val_loss: 1.0293 - val_accuracy: 0.9348 Epoch 310/500 128/6993 [..............................] - ETA: 0s - loss: 0.0172 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1054 - accuracy: 0.9912 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0975 - accuracy: 0.9905 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1203 - accuracy: 0.9914 3456/6993 [=============>................] - ETA: 0s - loss: 0.1114 - accuracy: 0.9899 4224/6993 [=================>............] - ETA: 0s - loss: 0.1016 - accuracy: 0.9905 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1205 - accuracy: 0.9892 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1143 - accuracy: 0.9891 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1212 - accuracy: 0.9888 6912/6993 [============================>.] - ETA: 0s - loss: 0.1178 - accuracy: 0.9886 6993/6993 [==============================] - 1s 90us/sample - loss: 0.1165 - accuracy: 0.9887 - val_loss: 0.9878 - val_accuracy: 0.9333 Epoch 311/500 128/6993 [..............................] - ETA: 0s - loss: 0.0287 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.2168 - accuracy: 0.9870 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1421 - accuracy: 0.9892 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1128 - accuracy: 0.9902 3456/6993 [=============>................] - ETA: 0s - loss: 0.1153 - accuracy: 0.9902 4352/6993 [=================>............] - ETA: 0s - loss: 0.1032 - accuracy: 0.9901 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0963 - accuracy: 0.9910 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0909 - accuracy: 0.9911 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0892 - accuracy: 0.9911 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0866 - accuracy: 0.9908 - val_loss: 1.0488 - val_accuracy: 0.9373 Epoch 312/500 128/6993 [..............................] - ETA: 0s - loss: 0.1174 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1261 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0792 - accuracy: 0.9922 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0740 - accuracy: 0.9897 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1688 - accuracy: 0.9888 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1685 - accuracy: 0.9883 4352/6993 [=================>............] - ETA: 0s - loss: 0.1643 - accuracy: 0.9871 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1495 - accuracy: 0.9881 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1355 - accuracy: 0.9883 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1246 - accuracy: 0.9889 6993/6993 [==============================] - 1s 87us/sample - loss: 0.1191 - accuracy: 0.9893 - val_loss: 1.0748 - val_accuracy: 0.9343 Epoch 313/500 128/6993 [..............................] - ETA: 0s - loss: 0.3803 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1000 - accuracy: 0.9944 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0945 - accuracy: 0.9916 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0833 - accuracy: 0.9926 3456/6993 [=============>................] - ETA: 0s - loss: 0.0855 - accuracy: 0.9916 4096/6993 [================>.............] - ETA: 0s - loss: 0.0894 - accuracy: 0.9912 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1318 - accuracy: 0.9908 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1165 - accuracy: 0.9916 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1087 - accuracy: 0.9911 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1118 - accuracy: 0.9909 6993/6993 [==============================] - 1s 91us/sample - loss: 0.1056 - accuracy: 0.9910 - val_loss: 1.0589 - val_accuracy: 0.9297 Epoch 314/500 128/6993 [..............................] - ETA: 0s - loss: 0.1025 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0602 - accuracy: 0.9870 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0665 - accuracy: 0.9872 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0957 - accuracy: 0.9878 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0794 - accuracy: 0.9876 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0767 - accuracy: 0.9874 4224/6993 [=================>............] - ETA: 0s - loss: 0.0806 - accuracy: 0.9867 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0845 - accuracy: 0.9870 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1022 - accuracy: 0.9869 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0958 - accuracy: 0.9877 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0947 - accuracy: 0.9878 - val_loss: 1.2402 - val_accuracy: 0.9247 Epoch 315/500 128/6993 [..............................] - ETA: 0s - loss: 0.7496 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.2232 - accuracy: 0.9859 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1730 - accuracy: 0.9867 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1325 - accuracy: 0.9883 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1194 - accuracy: 0.9887 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1198 - accuracy: 0.9891 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1196 - accuracy: 0.9891 4352/6993 [=================>............] - ETA: 0s - loss: 0.1109 - accuracy: 0.9883 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0989 - accuracy: 0.9888 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1075 - accuracy: 0.9888 6993/6993 [==============================] - 1s 89us/sample - loss: 0.1117 - accuracy: 0.9890 - val_loss: 1.1279 - val_accuracy: 0.9297 Epoch 316/500 128/6993 [..............................] - ETA: 0s - loss: 0.0157 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0758 - accuracy: 0.9922 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0820 - accuracy: 0.9906 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0982 - accuracy: 0.9881 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0798 - accuracy: 0.9894 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0673 - accuracy: 0.9904 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1244 - accuracy: 0.9895 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1166 - accuracy: 0.9902 6912/6993 [============================>.] - ETA: 0s - loss: 0.1086 - accuracy: 0.9900 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1093 - accuracy: 0.9900 - val_loss: 1.1989 - val_accuracy: 0.9287 Epoch 317/500 128/6993 [..............................] - ETA: 0s - loss: 0.0079 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0470 - accuracy: 0.9911 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0328 - accuracy: 0.9928 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0482 - accuracy: 0.9906 3456/6993 [=============>................] - ETA: 0s - loss: 0.0625 - accuracy: 0.9899 4352/6993 [=================>............] - ETA: 0s - loss: 0.0540 - accuracy: 0.9903 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0622 - accuracy: 0.9910 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0593 - accuracy: 0.9914 6912/6993 [============================>.] - ETA: 0s - loss: 0.0690 - accuracy: 0.9909 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0686 - accuracy: 0.9908 - val_loss: 1.2131 - val_accuracy: 0.9292 Epoch 318/500 128/6993 [..............................] - ETA: 0s - loss: 0.0339 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0762 - accuracy: 0.9922 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0987 - accuracy: 0.9906 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0842 - accuracy: 0.9907 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0943 - accuracy: 0.9900 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0811 - accuracy: 0.9908 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0798 - accuracy: 0.9914 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0965 - accuracy: 0.9912 6912/6993 [============================>.] - ETA: 0s - loss: 0.1204 - accuracy: 0.9905 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1190 - accuracy: 0.9906 - val_loss: 1.2000 - val_accuracy: 0.9272 Epoch 319/500 128/6993 [..............................] - ETA: 0s - loss: 0.1128 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.1256 - accuracy: 0.9875 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0693 - accuracy: 0.9906 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0490 - accuracy: 0.9927 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0477 - accuracy: 0.9926 3200/6993 [============>.................] - ETA: 0s - loss: 0.0443 - accuracy: 0.9934 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0554 - accuracy: 0.9922 4352/6993 [=================>............] - ETA: 0s - loss: 0.0649 - accuracy: 0.9915 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0745 - accuracy: 0.9912 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0823 - accuracy: 0.9906 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0749 - accuracy: 0.9912 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0883 - accuracy: 0.9907 - val_loss: 1.1461 - val_accuracy: 0.9282 Epoch 320/500 128/6993 [..............................] - ETA: 0s - loss: 0.2098 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0772 - accuracy: 0.9883 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0633 - accuracy: 0.9911 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1131 - accuracy: 0.9900 3456/6993 [=============>................] - ETA: 0s - loss: 0.1335 - accuracy: 0.9899 4224/6993 [=================>............] - ETA: 0s - loss: 0.1289 - accuracy: 0.9893 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1140 - accuracy: 0.9896 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1048 - accuracy: 0.9900 6784/6993 [============================>.] - ETA: 0s - loss: 0.0977 - accuracy: 0.9903 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0959 - accuracy: 0.9901 - val_loss: 1.3541 - val_accuracy: 0.9277 Epoch 321/500 128/6993 [..............................] - ETA: 0s - loss: 0.0186 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.3104 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.2155 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1542 - accuracy: 0.9900 3456/6993 [=============>................] - ETA: 0s - loss: 0.1511 - accuracy: 0.9887 4224/6993 [=================>............] - ETA: 0s - loss: 0.1320 - accuracy: 0.9884 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1272 - accuracy: 0.9880 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1297 - accuracy: 0.9882 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1280 - accuracy: 0.9886 6993/6993 [==============================] - 1s 87us/sample - loss: 0.1305 - accuracy: 0.9887 - val_loss: 1.2035 - val_accuracy: 0.9292 Epoch 322/500 128/6993 [..............................] - ETA: 0s - loss: 0.0505 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0888 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0910 - accuracy: 0.9898 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1050 - accuracy: 0.9887 3456/6993 [=============>................] - ETA: 0s - loss: 0.0875 - accuracy: 0.9896 4224/6993 [=================>............] - ETA: 0s - loss: 0.0769 - accuracy: 0.9903 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0713 - accuracy: 0.9900 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0662 - accuracy: 0.9902 6784/6993 [============================>.] - ETA: 0s - loss: 0.0654 - accuracy: 0.9900 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0637 - accuracy: 0.9903 - val_loss: 1.4673 - val_accuracy: 0.9307 Epoch 323/500 128/6993 [..............................] - ETA: 0s - loss: 0.1045 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0768 - accuracy: 0.9873 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0802 - accuracy: 0.9885 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0655 - accuracy: 0.9900 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0724 - accuracy: 0.9888 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0799 - accuracy: 0.9891 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0733 - accuracy: 0.9895 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0781 - accuracy: 0.9891 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1083 - accuracy: 0.9885 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1060 - accuracy: 0.9887 - val_loss: 1.6568 - val_accuracy: 0.9181 Epoch 324/500 128/6993 [..............................] - ETA: 0s - loss: 0.0987 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0553 - accuracy: 0.9961 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0465 - accuracy: 0.9943 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0741 - accuracy: 0.9922 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1031 - accuracy: 0.9896 3456/6993 [=============>................] - ETA: 0s - loss: 0.0911 - accuracy: 0.9887 4224/6993 [=================>............] - ETA: 0s - loss: 0.0816 - accuracy: 0.9886 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0826 - accuracy: 0.9886 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0726 - accuracy: 0.9896 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0747 - accuracy: 0.9889 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0741 - accuracy: 0.9888 - val_loss: 1.6239 - val_accuracy: 0.9201 Epoch 325/500 128/6993 [..............................] - ETA: 0s - loss: 0.3813 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1413 - accuracy: 0.9900 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1485 - accuracy: 0.9916 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1358 - accuracy: 0.9911 3456/6993 [=============>................] - ETA: 0s - loss: 0.1181 - accuracy: 0.9913 4352/6993 [=================>............] - ETA: 0s - loss: 0.1025 - accuracy: 0.9913 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0910 - accuracy: 0.9914 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1000 - accuracy: 0.9899 6912/6993 [============================>.] - ETA: 0s - loss: 0.0954 - accuracy: 0.9903 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0944 - accuracy: 0.9904 - val_loss: 1.2276 - val_accuracy: 0.9287 Epoch 326/500 128/6993 [..............................] - ETA: 0s - loss: 0.0012 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0705 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0536 - accuracy: 0.9911 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0496 - accuracy: 0.9914 3456/6993 [=============>................] - ETA: 0s - loss: 0.0819 - accuracy: 0.9893 4352/6993 [=================>............] - ETA: 0s - loss: 0.0897 - accuracy: 0.9883 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0762 - accuracy: 0.9899 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0672 - accuracy: 0.9912 6912/6993 [============================>.] - ETA: 0s - loss: 0.1482 - accuracy: 0.9909 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1467 - accuracy: 0.9910 - val_loss: 1.2580 - val_accuracy: 0.9277 Epoch 327/500 128/6993 [..............................] - ETA: 0s - loss: 0.0403 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1680 - accuracy: 0.9863 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1226 - accuracy: 0.9875 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1095 - accuracy: 0.9877 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1025 - accuracy: 0.9891 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0880 - accuracy: 0.9893 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0929 - accuracy: 0.9889 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0846 - accuracy: 0.9889 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0907 - accuracy: 0.9886 - val_loss: 1.2226 - val_accuracy: 0.9242 Epoch 328/500 128/6993 [..............................] - ETA: 0s - loss: 0.1981 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1194 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0993 - accuracy: 0.9866 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1007 - accuracy: 0.9875 3456/6993 [=============>................] - ETA: 0s - loss: 0.1080 - accuracy: 0.9876 4224/6993 [=================>............] - ETA: 0s - loss: 0.1003 - accuracy: 0.9875 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0975 - accuracy: 0.9874 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1081 - accuracy: 0.9870 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1164 - accuracy: 0.9866 6993/6993 [==============================] - 1s 89us/sample - loss: 0.1152 - accuracy: 0.9864 - val_loss: 1.0901 - val_accuracy: 0.9323 Epoch 329/500 128/6993 [..............................] - ETA: 0s - loss: 0.0130 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0770 - accuracy: 0.9909 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0677 - accuracy: 0.9889 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0727 - accuracy: 0.9867 3072/6993 [============>.................] - ETA: 0s - loss: 0.0922 - accuracy: 0.9880 3968/6993 [================>.............] - ETA: 0s - loss: 0.1160 - accuracy: 0.9859 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1152 - accuracy: 0.9860 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1233 - accuracy: 0.9854 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1123 - accuracy: 0.9865 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1239 - accuracy: 0.9871 - val_loss: 1.1084 - val_accuracy: 0.9312 Epoch 330/500 128/6993 [..............................] - ETA: 0s - loss: 0.0039 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0857 - accuracy: 0.9893 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0883 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0809 - accuracy: 0.9896 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1001 - accuracy: 0.9891 4352/6993 [=================>............] - ETA: 0s - loss: 0.1215 - accuracy: 0.9885 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1117 - accuracy: 0.9886 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1115 - accuracy: 0.9885 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1052 - accuracy: 0.9887 6993/6993 [==============================] - 1s 84us/sample - loss: 0.1009 - accuracy: 0.9890 - val_loss: 1.2532 - val_accuracy: 0.9272 Epoch 331/500 128/6993 [..............................] - ETA: 0s - loss: 0.0143 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0588 - accuracy: 0.9922 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0529 - accuracy: 0.9904 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0460 - accuracy: 0.9918 3328/6993 [=============>................] - ETA: 0s - loss: 0.0438 - accuracy: 0.9913 4224/6993 [=================>............] - ETA: 0s - loss: 0.0394 - accuracy: 0.9920 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0426 - accuracy: 0.9908 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0432 - accuracy: 0.9910 6784/6993 [============================>.] - ETA: 0s - loss: 0.0473 - accuracy: 0.9907 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0475 - accuracy: 0.9903 - val_loss: 1.1618 - val_accuracy: 0.9282 Epoch 332/500 128/6993 [..............................] - ETA: 0s - loss: 0.0612 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0637 - accuracy: 0.9893 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0425 - accuracy: 0.9932 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0460 - accuracy: 0.9937 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0473 - accuracy: 0.9925 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0502 - accuracy: 0.9924 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0566 - accuracy: 0.9914 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0535 - accuracy: 0.9911 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0542 - accuracy: 0.9910 - val_loss: 1.3554 - val_accuracy: 0.9373 Epoch 333/500 128/6993 [..............................] - ETA: 0s - loss: 0.0721 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1079 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0823 - accuracy: 0.9898 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1306 - accuracy: 0.9887 3328/6993 [=============>................] - ETA: 0s - loss: 0.1084 - accuracy: 0.9892 4224/6993 [=================>............] - ETA: 0s - loss: 0.1218 - accuracy: 0.9886 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1095 - accuracy: 0.9891 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1030 - accuracy: 0.9893 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1104 - accuracy: 0.9886 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1085 - accuracy: 0.9884 6993/6993 [==============================] - 1s 89us/sample - loss: 0.1072 - accuracy: 0.9886 - val_loss: 1.1337 - val_accuracy: 0.9338 Epoch 334/500 128/6993 [..............................] - ETA: 0s - loss: 0.1334 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0393 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0761 - accuracy: 0.9901 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0537 - accuracy: 0.9922 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0764 - accuracy: 0.9895 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0854 - accuracy: 0.9905 4224/6993 [=================>............] - ETA: 0s - loss: 0.0801 - accuracy: 0.9905 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0898 - accuracy: 0.9893 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0893 - accuracy: 0.9891 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0961 - accuracy: 0.9886 6784/6993 [============================>.] - ETA: 0s - loss: 0.0987 - accuracy: 0.9885 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0966 - accuracy: 0.9887 - val_loss: 1.0478 - val_accuracy: 0.9368 Epoch 335/500 128/6993 [..............................] - ETA: 0s - loss: 0.0530 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0193 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0241 - accuracy: 0.9922 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0265 - accuracy: 0.9914 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0609 - accuracy: 0.9908 4352/6993 [=================>............] - ETA: 0s - loss: 0.0584 - accuracy: 0.9903 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0645 - accuracy: 0.9910 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0781 - accuracy: 0.9910 6912/6993 [============================>.] - ETA: 0s - loss: 0.0730 - accuracy: 0.9910 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0725 - accuracy: 0.9908 - val_loss: 1.4082 - val_accuracy: 0.9338 Epoch 336/500 128/6993 [..............................] - ETA: 0s - loss: 0.0255 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0548 - accuracy: 0.9896 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0621 - accuracy: 0.9891 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0583 - accuracy: 0.9891 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0482 - accuracy: 0.9906 3200/6993 [============>.................] - ETA: 0s - loss: 0.0485 - accuracy: 0.9912 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0561 - accuracy: 0.9917 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0628 - accuracy: 0.9904 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0944 - accuracy: 0.9903 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1025 - accuracy: 0.9894 6912/6993 [============================>.] - ETA: 0s - loss: 0.1030 - accuracy: 0.9889 6993/6993 [==============================] - 1s 88us/sample - loss: 0.1021 - accuracy: 0.9888 - val_loss: 1.1092 - val_accuracy: 0.9323 Epoch 337/500 128/6993 [..............................] - ETA: 0s - loss: 0.0941 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1344 - accuracy: 0.9877 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0877 - accuracy: 0.9904 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0877 - accuracy: 0.9889 3200/6993 [============>.................] - ETA: 0s - loss: 0.0776 - accuracy: 0.9881 3968/6993 [================>.............] - ETA: 0s - loss: 0.1044 - accuracy: 0.9882 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1087 - accuracy: 0.9887 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1162 - accuracy: 0.9873 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1087 - accuracy: 0.9881 6993/6993 [==============================] - 1s 87us/sample - loss: 0.1202 - accuracy: 0.9880 - val_loss: 1.2525 - val_accuracy: 0.9302 Epoch 338/500 128/6993 [..............................] - ETA: 0s - loss: 0.0043 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.1611 - accuracy: 0.9855 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1230 - accuracy: 0.9858 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1087 - accuracy: 0.9868 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1024 - accuracy: 0.9870 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1035 - accuracy: 0.9870 3200/6993 [============>.................] - ETA: 0s - loss: 0.1087 - accuracy: 0.9881 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0988 - accuracy: 0.9879 4352/6993 [=================>............] - ETA: 0s - loss: 0.0948 - accuracy: 0.9881 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0859 - accuracy: 0.9886 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0802 - accuracy: 0.9884 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0799 - accuracy: 0.9874 6993/6993 [==============================] - 1s 102us/sample - loss: 0.0769 - accuracy: 0.9876 - val_loss: 1.2099 - val_accuracy: 0.9328 Epoch 339/500 128/6993 [..............................] - ETA: 0s - loss: 0.0181 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0628 - accuracy: 0.9900 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0531 - accuracy: 0.9911 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0594 - accuracy: 0.9914 3456/6993 [=============>................] - ETA: 0s - loss: 0.0462 - accuracy: 0.9928 4352/6993 [=================>............] - ETA: 0s - loss: 0.0537 - accuracy: 0.9908 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0710 - accuracy: 0.9897 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1078 - accuracy: 0.9886 6993/6993 [==============================] - 1s 77us/sample - loss: 0.1032 - accuracy: 0.9887 - val_loss: 1.1636 - val_accuracy: 0.9323 Epoch 340/500 128/6993 [..............................] - ETA: 0s - loss: 0.0093 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2931 - accuracy: 0.9902 1792/6993 [======>.......................] - ETA: 0s - loss: 0.2092 - accuracy: 0.9911 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1624 - accuracy: 0.9926 3200/6993 [============>.................] - ETA: 0s - loss: 0.1711 - accuracy: 0.9912 3968/6993 [================>.............] - ETA: 0s - loss: 0.1525 - accuracy: 0.9909 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1470 - accuracy: 0.9900 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1302 - accuracy: 0.9907 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1194 - accuracy: 0.9907 6784/6993 [============================>.] - ETA: 0s - loss: 0.1107 - accuracy: 0.9909 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1077 - accuracy: 0.9910 - val_loss: 1.0874 - val_accuracy: 0.9328 Epoch 341/500 128/6993 [..............................] - ETA: 0s - loss: 0.0107 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0837 - accuracy: 0.9902 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1114 - accuracy: 0.9916 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1110 - accuracy: 0.9903 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0956 - accuracy: 0.9900 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0918 - accuracy: 0.9891 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0920 - accuracy: 0.9890 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0846 - accuracy: 0.9893 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0852 - accuracy: 0.9890 - val_loss: 1.1854 - val_accuracy: 0.9343 Epoch 342/500 128/6993 [..............................] - ETA: 0s - loss: 0.0287 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1174 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0947 - accuracy: 0.9922 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0976 - accuracy: 0.9889 3200/6993 [============>.................] - ETA: 0s - loss: 0.0857 - accuracy: 0.9900 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1130 - accuracy: 0.9898 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0985 - accuracy: 0.9902 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0951 - accuracy: 0.9901 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0882 - accuracy: 0.9909 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0821 - accuracy: 0.9911 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0785 - accuracy: 0.9916 - val_loss: 1.2449 - val_accuracy: 0.9338 Epoch 343/500 128/6993 [..............................] - ETA: 0s - loss: 0.2145 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1676 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1297 - accuracy: 0.9898 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1548 - accuracy: 0.9893 3328/6993 [=============>................] - ETA: 0s - loss: 0.1303 - accuracy: 0.9907 4224/6993 [=================>............] - ETA: 0s - loss: 0.1357 - accuracy: 0.9898 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1241 - accuracy: 0.9891 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1282 - accuracy: 0.9892 6784/6993 [============================>.] - ETA: 0s - loss: 0.1240 - accuracy: 0.9892 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1262 - accuracy: 0.9891 - val_loss: 1.2613 - val_accuracy: 0.9373 Epoch 344/500 128/6993 [..............................] - ETA: 0s - loss: 0.0024 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0387 - accuracy: 0.9863 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0941 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0775 - accuracy: 0.9900 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1269 - accuracy: 0.9886 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1203 - accuracy: 0.9888 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1299 - accuracy: 0.9887 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1196 - accuracy: 0.9892 6993/6993 [==============================] - 1s 82us/sample - loss: 0.1128 - accuracy: 0.9894 - val_loss: 1.2101 - val_accuracy: 0.9312 Epoch 345/500 128/6993 [..............................] - ETA: 0s - loss: 0.0167 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0825 - accuracy: 0.9911 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0700 - accuracy: 0.9900 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0672 - accuracy: 0.9907 3456/6993 [=============>................] - ETA: 0s - loss: 0.0582 - accuracy: 0.9916 4352/6993 [=================>............] - ETA: 0s - loss: 0.0568 - accuracy: 0.9917 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0544 - accuracy: 0.9918 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0702 - accuracy: 0.9917 6784/6993 [============================>.] - ETA: 0s - loss: 0.0643 - accuracy: 0.9919 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0657 - accuracy: 0.9920 - val_loss: 1.3293 - val_accuracy: 0.9363 Epoch 346/500 128/6993 [..............................] - ETA: 0s - loss: 0.0210 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0164 - accuracy: 0.9948 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0592 - accuracy: 0.9936 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0907 - accuracy: 0.9911 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0914 - accuracy: 0.9926 3200/6993 [============>.................] - ETA: 0s - loss: 0.1275 - accuracy: 0.9903 3968/6993 [================>.............] - ETA: 0s - loss: 0.1458 - accuracy: 0.9907 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1435 - accuracy: 0.9902 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1347 - accuracy: 0.9894 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1252 - accuracy: 0.9892 6993/6993 [==============================] - 1s 96us/sample - loss: 0.1199 - accuracy: 0.9887 - val_loss: 1.1096 - val_accuracy: 0.9393 Epoch 347/500 128/6993 [..............................] - ETA: 0s - loss: 0.0239 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0464 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0474 - accuracy: 0.9915 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0385 - accuracy: 0.9922 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0355 - accuracy: 0.9922 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0464 - accuracy: 0.9929 3456/6993 [=============>................] - ETA: 0s - loss: 0.0484 - accuracy: 0.9922 4096/6993 [================>.............] - ETA: 0s - loss: 0.0625 - accuracy: 0.9924 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0665 - accuracy: 0.9922 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0840 - accuracy: 0.9914 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0824 - accuracy: 0.9905 6784/6993 [============================>.] - ETA: 0s - loss: 0.0780 - accuracy: 0.9904 6993/6993 [==============================] - 1s 103us/sample - loss: 0.0760 - accuracy: 0.9906 - val_loss: 1.3711 - val_accuracy: 0.9292 Epoch 348/500 128/6993 [..............................] - ETA: 0s - loss: 0.3916 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9944 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0614 - accuracy: 0.9944 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0682 - accuracy: 0.9933 3456/6993 [=============>................] - ETA: 0s - loss: 0.0695 - accuracy: 0.9928 4224/6993 [=================>............] - ETA: 0s - loss: 0.0682 - accuracy: 0.9927 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0646 - accuracy: 0.9924 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0654 - accuracy: 0.9917 6784/6993 [============================>.] - ETA: 0s - loss: 0.0723 - accuracy: 0.9912 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0706 - accuracy: 0.9913 - val_loss: 1.2416 - val_accuracy: 0.9317 Epoch 349/500 128/6993 [..............................] - ETA: 0s - loss: 0.0108 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0284 - accuracy: 0.9911 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0301 - accuracy: 0.9927 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0708 - accuracy: 0.9914 3328/6993 [=============>................] - ETA: 0s - loss: 0.0605 - accuracy: 0.9916 3968/6993 [================>.............] - ETA: 0s - loss: 0.0583 - accuracy: 0.9914 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0741 - accuracy: 0.9889 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0867 - accuracy: 0.9873 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0944 - accuracy: 0.9874 6912/6993 [============================>.] - ETA: 0s - loss: 0.0917 - accuracy: 0.9876 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0906 - accuracy: 0.9877 - val_loss: 1.2782 - val_accuracy: 0.9302 Epoch 350/500 128/6993 [..............................] - ETA: 0s - loss: 0.0147 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1548 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1489 - accuracy: 0.9905 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1309 - accuracy: 0.9874 3456/6993 [=============>................] - ETA: 0s - loss: 0.1151 - accuracy: 0.9887 4224/6993 [=================>............] - ETA: 0s - loss: 0.1153 - accuracy: 0.9889 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1153 - accuracy: 0.9893 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1060 - accuracy: 0.9896 6784/6993 [============================>.] - ETA: 0s - loss: 0.0938 - accuracy: 0.9904 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0918 - accuracy: 0.9903 - val_loss: 1.3173 - val_accuracy: 0.9297 Epoch 351/500 128/6993 [..............................] - ETA: 0s - loss: 0.0062 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0778 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0636 - accuracy: 0.9916 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0749 - accuracy: 0.9905 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1555 - accuracy: 0.9879 3456/6993 [=============>................] - ETA: 0s - loss: 0.1495 - accuracy: 0.9887 4096/6993 [================>.............] - ETA: 0s - loss: 0.1349 - accuracy: 0.9890 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1208 - accuracy: 0.9899 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1142 - accuracy: 0.9892 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1111 - accuracy: 0.9894 6993/6993 [==============================] - 1s 92us/sample - loss: 0.1079 - accuracy: 0.9890 - val_loss: 1.4895 - val_accuracy: 0.9272 Epoch 352/500 128/6993 [..............................] - ETA: 0s - loss: 0.0629 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0254 - accuracy: 0.9922 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0612 - accuracy: 0.9928 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0752 - accuracy: 0.9926 3328/6993 [=============>................] - ETA: 0s - loss: 0.0768 - accuracy: 0.9919 4096/6993 [================>.............] - ETA: 0s - loss: 0.0837 - accuracy: 0.9910 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0840 - accuracy: 0.9905 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0832 - accuracy: 0.9910 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0753 - accuracy: 0.9913 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0767 - accuracy: 0.9914 - val_loss: 1.4124 - val_accuracy: 0.9307 Epoch 353/500 128/6993 [..............................] - ETA: 0s - loss: 0.0133 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0487 - accuracy: 0.9951 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0724 - accuracy: 0.9916 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0637 - accuracy: 0.9914 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0632 - accuracy: 0.9908 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0872 - accuracy: 0.9904 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0911 - accuracy: 0.9903 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1156 - accuracy: 0.9896 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1072 - accuracy: 0.9898 - val_loss: 1.4645 - val_accuracy: 0.9282 Epoch 354/500 128/6993 [..............................] - ETA: 0s - loss: 0.0664 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0576 - accuracy: 0.9896 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0399 - accuracy: 0.9922 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0783 - accuracy: 0.9900 3200/6993 [============>.................] - ETA: 0s - loss: 0.1525 - accuracy: 0.9897 3968/6993 [================>.............] - ETA: 0s - loss: 0.1347 - accuracy: 0.9899 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1607 - accuracy: 0.9891 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1579 - accuracy: 0.9890 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1567 - accuracy: 0.9882 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1478 - accuracy: 0.9883 - val_loss: 1.1978 - val_accuracy: 0.9328 Epoch 355/500 128/6993 [..............................] - ETA: 0s - loss: 0.0551 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0667 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1024 - accuracy: 0.9900 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1064 - accuracy: 0.9888 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1980 - accuracy: 0.9894 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1813 - accuracy: 0.9893 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1695 - accuracy: 0.9888 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1505 - accuracy: 0.9896 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1437 - accuracy: 0.9897 - val_loss: 1.0802 - val_accuracy: 0.9333 Epoch 356/500 128/6993 [..............................] - ETA: 0s - loss: 0.0073 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.2593 - accuracy: 0.9911 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1869 - accuracy: 0.9909 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1697 - accuracy: 0.9890 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1523 - accuracy: 0.9897 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1276 - accuracy: 0.9900 4224/6993 [=================>............] - ETA: 0s - loss: 0.1133 - accuracy: 0.9893 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1312 - accuracy: 0.9887 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1275 - accuracy: 0.9889 6912/6993 [============================>.] - ETA: 0s - loss: 0.1210 - accuracy: 0.9891 6993/6993 [==============================] - 1s 89us/sample - loss: 0.1196 - accuracy: 0.9893 - val_loss: 1.1529 - val_accuracy: 0.9338 Epoch 357/500 128/6993 [..............................] - ETA: 0s - loss: 0.0077 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2674 - accuracy: 0.9854 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1828 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1682 - accuracy: 0.9866 3456/6993 [=============>................] - ETA: 0s - loss: 0.1594 - accuracy: 0.9864 4352/6993 [=================>............] - ETA: 0s - loss: 0.1432 - accuracy: 0.9876 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1269 - accuracy: 0.9883 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1112 - accuracy: 0.9890 6784/6993 [============================>.] - ETA: 0s - loss: 0.1128 - accuracy: 0.9894 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1128 - accuracy: 0.9893 - val_loss: 1.0691 - val_accuracy: 0.9388 Epoch 358/500 128/6993 [..............................] - ETA: 0s - loss: 0.0018 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0320 - accuracy: 0.9911 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0427 - accuracy: 0.9904 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0642 - accuracy: 0.9891 3328/6993 [=============>................] - ETA: 0s - loss: 0.0675 - accuracy: 0.9892 4224/6993 [=================>............] - ETA: 0s - loss: 0.0728 - accuracy: 0.9889 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0670 - accuracy: 0.9890 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0680 - accuracy: 0.9891 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0735 - accuracy: 0.9892 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0705 - accuracy: 0.9894 - val_loss: 1.2312 - val_accuracy: 0.9323 Epoch 359/500 128/6993 [..............................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2106 - accuracy: 0.9902 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1563 - accuracy: 0.9905 2688/6993 [==========>...................] - ETA: 0s - loss: 0.3290 - accuracy: 0.9888 3456/6993 [=============>................] - ETA: 0s - loss: 0.2904 - accuracy: 0.9876 4352/6993 [=================>............] - ETA: 0s - loss: 0.2488 - accuracy: 0.9881 5248/6993 [=====================>........] - ETA: 0s - loss: 0.2183 - accuracy: 0.9882 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1994 - accuracy: 0.9879 6912/6993 [============================>.] - ETA: 0s - loss: 0.1780 - accuracy: 0.9880 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1766 - accuracy: 0.9880 - val_loss: 1.0980 - val_accuracy: 0.9368 Epoch 360/500 128/6993 [..............................] - ETA: 0s - loss: 0.0321 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0686 - accuracy: 0.9873 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0543 - accuracy: 0.9883 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0879 - accuracy: 0.9875 3328/6993 [=============>................] - ETA: 0s - loss: 0.0837 - accuracy: 0.9880 4096/6993 [================>.............] - ETA: 0s - loss: 0.0714 - accuracy: 0.9893 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0701 - accuracy: 0.9891 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0653 - accuracy: 0.9901 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0967 - accuracy: 0.9897 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0961 - accuracy: 0.9897 - val_loss: 1.2875 - val_accuracy: 0.9302 Epoch 361/500 128/6993 [..............................] - ETA: 0s - loss: 0.0223 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0679 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0583 - accuracy: 0.9911 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0601 - accuracy: 0.9911 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0608 - accuracy: 0.9908 4352/6993 [=================>............] - ETA: 0s - loss: 0.0596 - accuracy: 0.9917 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1179 - accuracy: 0.9909 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1190 - accuracy: 0.9904 6993/6993 [==============================] - 1s 76us/sample - loss: 0.1104 - accuracy: 0.9903 - val_loss: 1.2651 - val_accuracy: 0.9297 Epoch 362/500 128/6993 [..............................] - ETA: 0s - loss: 0.0896 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0398 - accuracy: 0.9893 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0416 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0421 - accuracy: 0.9911 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0374 - accuracy: 0.9911 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0603 - accuracy: 0.9911 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0605 - accuracy: 0.9907 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0584 - accuracy: 0.9903 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0585 - accuracy: 0.9903 - val_loss: 1.1334 - val_accuracy: 0.9358 Epoch 363/500 128/6993 [..............................] - ETA: 0s - loss: 0.0599 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0500 - accuracy: 0.9911 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0588 - accuracy: 0.9904 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0486 - accuracy: 0.9914 3456/6993 [=============>................] - ETA: 0s - loss: 0.0606 - accuracy: 0.9896 4352/6993 [=================>............] - ETA: 0s - loss: 0.0544 - accuracy: 0.9901 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0524 - accuracy: 0.9906 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0527 - accuracy: 0.9905 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0537 - accuracy: 0.9905 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0528 - accuracy: 0.9906 - val_loss: 1.5944 - val_accuracy: 0.9343 Epoch 364/500 128/6993 [..............................] - ETA: 0s - loss: 0.0525 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1114 - accuracy: 0.9844 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1732 - accuracy: 0.9865 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1788 - accuracy: 0.9870 3456/6993 [=============>................] - ETA: 0s - loss: 0.1851 - accuracy: 0.9870 4352/6993 [=================>............] - ETA: 0s - loss: 0.1966 - accuracy: 0.9876 4864/6993 [===================>..........] - ETA: 0s - loss: 0.2123 - accuracy: 0.9873 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1894 - accuracy: 0.9872 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1878 - accuracy: 0.9875 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1744 - accuracy: 0.9881 - val_loss: 1.1648 - val_accuracy: 0.9333 Epoch 365/500 128/6993 [..............................] - ETA: 0s - loss: 0.0040 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.1467 - accuracy: 0.9922 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1349 - accuracy: 0.9922 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1220 - accuracy: 0.9883 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0997 - accuracy: 0.9898 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0873 - accuracy: 0.9902 4096/6993 [================>.............] - ETA: 0s - loss: 0.0896 - accuracy: 0.9895 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0909 - accuracy: 0.9892 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0961 - accuracy: 0.9888 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0902 - accuracy: 0.9891 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0918 - accuracy: 0.9890 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0887 - accuracy: 0.9893 - val_loss: 1.1440 - val_accuracy: 0.9312 Epoch 366/500 128/6993 [..............................] - ETA: 0s - loss: 1.7704e-04 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0258 - accuracy: 0.9955 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0467 - accuracy: 0.9939 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0398 - accuracy: 0.9926 3200/6993 [============>.................] - ETA: 0s - loss: 0.0347 - accuracy: 0.9931 3968/6993 [================>.............] - ETA: 0s - loss: 0.0550 - accuracy: 0.9922 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0597 - accuracy: 0.9926 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0651 - accuracy: 0.9918 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0703 - accuracy: 0.9917 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0692 - accuracy: 0.9914 - val_loss: 1.6061 - val_accuracy: 0.9358 Epoch 367/500 128/6993 [..............................] - ETA: 0s - loss: 0.0906 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0576 - accuracy: 0.9911 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1727 - accuracy: 0.9910 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1598 - accuracy: 0.9875 3456/6993 [=============>................] - ETA: 0s - loss: 0.1751 - accuracy: 0.9855 4224/6993 [=================>............] - ETA: 0s - loss: 0.1499 - accuracy: 0.9865 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1680 - accuracy: 0.9865 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1521 - accuracy: 0.9870 6784/6993 [============================>.] - ETA: 0s - loss: 0.1431 - accuracy: 0.9875 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1415 - accuracy: 0.9877 - val_loss: 1.3203 - val_accuracy: 0.9277 Epoch 368/500 128/6993 [..............................] - ETA: 0s - loss: 0.0025 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0433 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0930 - accuracy: 0.9888 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1028 - accuracy: 0.9895 3456/6993 [=============>................] - ETA: 0s - loss: 0.0821 - accuracy: 0.9902 4224/6993 [=================>............] - ETA: 0s - loss: 0.0699 - accuracy: 0.9912 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0666 - accuracy: 0.9912 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0815 - accuracy: 0.9908 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0737 - accuracy: 0.9911 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0748 - accuracy: 0.9911 - val_loss: 1.1832 - val_accuracy: 0.9358 Epoch 369/500 128/6993 [..............................] - ETA: 0s - loss: 0.3081 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0748 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0645 - accuracy: 0.9892 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0492 - accuracy: 0.9914 3328/6993 [=============>................] - ETA: 0s - loss: 0.1286 - accuracy: 0.9892 4096/6993 [================>.............] - ETA: 0s - loss: 0.1154 - accuracy: 0.9878 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1211 - accuracy: 0.9878 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1535 - accuracy: 0.9880 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1417 - accuracy: 0.9886 6784/6993 [============================>.] - ETA: 0s - loss: 0.1326 - accuracy: 0.9889 6993/6993 [==============================] - 1s 93us/sample - loss: 0.1298 - accuracy: 0.9888 - val_loss: 1.3652 - val_accuracy: 0.9257 Epoch 370/500 128/6993 [..............................] - ETA: 0s - loss: 0.0785 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0853 - accuracy: 0.9870 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1149 - accuracy: 0.9883 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1291 - accuracy: 0.9874 3072/6993 [============>.................] - ETA: 0s - loss: 0.1157 - accuracy: 0.9889 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1158 - accuracy: 0.9880 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1160 - accuracy: 0.9885 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1194 - accuracy: 0.9879 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1108 - accuracy: 0.9881 6993/6993 [==============================] - 1s 87us/sample - loss: 0.1029 - accuracy: 0.9881 - val_loss: 1.3858 - val_accuracy: 0.9353 Epoch 371/500 128/6993 [..............................] - ETA: 0s - loss: 0.0168 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1781 - accuracy: 0.9834 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1532 - accuracy: 0.9838 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1165 - accuracy: 0.9859 3456/6993 [=============>................] - ETA: 0s - loss: 0.1249 - accuracy: 0.9873 4096/6993 [================>.............] - ETA: 0s - loss: 0.1193 - accuracy: 0.9875 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1203 - accuracy: 0.9862 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1099 - accuracy: 0.9877 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1002 - accuracy: 0.9881 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1068 - accuracy: 0.9880 - val_loss: 1.4651 - val_accuracy: 0.9252 Epoch 372/500 128/6993 [..............................] - ETA: 0s - loss: 0.0070 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.1070 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0715 - accuracy: 0.9894 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0701 - accuracy: 0.9883 3456/6993 [=============>................] - ETA: 0s - loss: 0.0947 - accuracy: 0.9878 4224/6993 [=================>............] - ETA: 0s - loss: 0.1014 - accuracy: 0.9872 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1266 - accuracy: 0.9874 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1356 - accuracy: 0.9871 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1304 - accuracy: 0.9872 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1309 - accuracy: 0.9866 - val_loss: 1.3760 - val_accuracy: 0.9323 Epoch 373/500 128/6993 [..............................] - ETA: 0s - loss: 0.0110 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0601 - accuracy: 0.9951 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0474 - accuracy: 0.9927 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0735 - accuracy: 0.9929 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0757 - accuracy: 0.9933 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0668 - accuracy: 0.9926 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0745 - accuracy: 0.9920 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0732 - accuracy: 0.9920 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0704 - accuracy: 0.9923 - val_loss: 1.3882 - val_accuracy: 0.9312 Epoch 374/500 128/6993 [..............................] - ETA: 0s - loss: 0.1020 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0294 - accuracy: 0.9967 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0471 - accuracy: 0.9955 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0400 - accuracy: 0.9951 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0463 - accuracy: 0.9946 3456/6993 [=============>................] - ETA: 0s - loss: 0.0575 - accuracy: 0.9939 3968/6993 [================>.............] - ETA: 0s - loss: 0.0581 - accuracy: 0.9940 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0620 - accuracy: 0.9922 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0638 - accuracy: 0.9918 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0691 - accuracy: 0.9915 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0697 - accuracy: 0.9914 6993/6993 [==============================] - 1s 103us/sample - loss: 0.0666 - accuracy: 0.9916 - val_loss: 1.4937 - val_accuracy: 0.9323 Epoch 375/500 128/6993 [..............................] - ETA: 0s - loss: 0.0102 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0803 - accuracy: 0.9893 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0629 - accuracy: 0.9911 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0690 - accuracy: 0.9911 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0805 - accuracy: 0.9914 4352/6993 [=================>............] - ETA: 0s - loss: 0.0862 - accuracy: 0.9901 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0796 - accuracy: 0.9902 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1024 - accuracy: 0.9898 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1068 - accuracy: 0.9901 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1293 - accuracy: 0.9896 - val_loss: 1.6533 - val_accuracy: 0.9262 Epoch 376/500 128/6993 [..............................] - ETA: 0s - loss: 0.0271 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.2362 - accuracy: 0.9779 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1171 - accuracy: 0.9874 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1039 - accuracy: 0.9887 3328/6993 [=============>................] - ETA: 0s - loss: 0.0902 - accuracy: 0.9898 4096/6993 [================>.............] - ETA: 0s - loss: 0.0924 - accuracy: 0.9895 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0902 - accuracy: 0.9888 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0948 - accuracy: 0.9891 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0969 - accuracy: 0.9889 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0911 - accuracy: 0.9890 - val_loss: 1.2459 - val_accuracy: 0.9348 Epoch 377/500 128/6993 [..............................] - ETA: 0s - loss: 0.0027 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0336 - accuracy: 0.9951 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0652 - accuracy: 0.9922 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0810 - accuracy: 0.9918 3456/6993 [=============>................] - ETA: 0s - loss: 0.0857 - accuracy: 0.9910 4352/6993 [=================>............] - ETA: 0s - loss: 0.0869 - accuracy: 0.9910 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0794 - accuracy: 0.9916 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0841 - accuracy: 0.9905 6784/6993 [============================>.] - ETA: 0s - loss: 0.0795 - accuracy: 0.9912 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0782 - accuracy: 0.9913 - val_loss: 1.3831 - val_accuracy: 0.9353 Epoch 378/500 128/6993 [..............................] - ETA: 0s - loss: 0.0021 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0987 - accuracy: 0.9912 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0738 - accuracy: 0.9917 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9925 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0584 - accuracy: 0.9933 4352/6993 [=================>............] - ETA: 0s - loss: 0.0524 - accuracy: 0.9938 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0580 - accuracy: 0.9928 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0757 - accuracy: 0.9913 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0721 - accuracy: 0.9908 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0707 - accuracy: 0.9908 - val_loss: 1.4971 - val_accuracy: 0.9333 Epoch 379/500 128/6993 [..............................] - ETA: 0s - loss: 0.0072 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0331 - accuracy: 0.9933 1792/6993 [======>.......................] - ETA: 0s - loss: 0.2135 - accuracy: 0.9927 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1895 - accuracy: 0.9914 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1474 - accuracy: 0.9922 4352/6993 [=================>............] - ETA: 0s - loss: 0.1276 - accuracy: 0.9920 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1323 - accuracy: 0.9916 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1308 - accuracy: 0.9917 6912/6993 [============================>.] - ETA: 0s - loss: 0.1398 - accuracy: 0.9910 6993/6993 [==============================] - 1s 76us/sample - loss: 0.1383 - accuracy: 0.9911 - val_loss: 1.2896 - val_accuracy: 0.9267 Epoch 380/500 128/6993 [..............................] - ETA: 0s - loss: 0.0294 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0232 - accuracy: 0.9933 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0632 - accuracy: 0.9905 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0595 - accuracy: 0.9902 3456/6993 [=============>................] - ETA: 0s - loss: 0.0541 - accuracy: 0.9902 4352/6993 [=================>............] - ETA: 0s - loss: 0.0594 - accuracy: 0.9906 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0589 - accuracy: 0.9909 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0521 - accuracy: 0.9920 6912/6993 [============================>.] - ETA: 0s - loss: 0.0654 - accuracy: 0.9915 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0646 - accuracy: 0.9916 - val_loss: 1.6436 - val_accuracy: 0.9292 Epoch 381/500 128/6993 [..............................] - ETA: 0s - loss: 0.0201 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.1617 - accuracy: 0.9896 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1474 - accuracy: 0.9934 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1118 - accuracy: 0.9930 3328/6993 [=============>................] - ETA: 0s - loss: 0.1001 - accuracy: 0.9916 4224/6993 [=================>............] - ETA: 0s - loss: 0.1076 - accuracy: 0.9915 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0933 - accuracy: 0.9922 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1152 - accuracy: 0.9924 6784/6993 [============================>.] - ETA: 0s - loss: 0.1140 - accuracy: 0.9920 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1118 - accuracy: 0.9918 - val_loss: 1.5810 - val_accuracy: 0.9353 Epoch 382/500 128/6993 [..............................] - ETA: 0s - loss: 0.0354 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.5057 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.2950 - accuracy: 0.9872 2560/6993 [=========>....................] - ETA: 0s - loss: 0.2735 - accuracy: 0.9867 3456/6993 [=============>................] - ETA: 0s - loss: 0.2281 - accuracy: 0.9887 4352/6993 [=================>............] - ETA: 0s - loss: 0.1968 - accuracy: 0.9894 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1718 - accuracy: 0.9902 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1561 - accuracy: 0.9890 6912/6993 [============================>.] - ETA: 0s - loss: 0.1519 - accuracy: 0.9893 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1502 - accuracy: 0.9894 - val_loss: 1.6606 - val_accuracy: 0.9373 Epoch 383/500 128/6993 [..............................] - ETA: 0s - loss: 0.0171 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0807 - accuracy: 0.9834 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1093 - accuracy: 0.9870 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0908 - accuracy: 0.9886 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1258 - accuracy: 0.9880 4352/6993 [=================>............] - ETA: 0s - loss: 0.1301 - accuracy: 0.9867 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1210 - accuracy: 0.9871 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1169 - accuracy: 0.9875 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1208 - accuracy: 0.9877 6993/6993 [==============================] - 1s 89us/sample - loss: 0.1121 - accuracy: 0.9881 - val_loss: 1.4684 - val_accuracy: 0.9353 Epoch 384/500 128/6993 [..............................] - ETA: 0s - loss: 0.0883 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0858 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0717 - accuracy: 0.9915 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0508 - accuracy: 0.9935 3200/6993 [============>.................] - ETA: 0s - loss: 0.0455 - accuracy: 0.9931 4096/6993 [================>.............] - ETA: 0s - loss: 0.0631 - accuracy: 0.9934 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0590 - accuracy: 0.9934 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0593 - accuracy: 0.9927 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0661 - accuracy: 0.9922 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0674 - accuracy: 0.9920 - val_loss: 1.3080 - val_accuracy: 0.9297 Epoch 385/500 128/6993 [..............................] - ETA: 0s - loss: 0.3998 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0942 - accuracy: 0.9912 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0636 - accuracy: 0.9922 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0508 - accuracy: 0.9926 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0594 - accuracy: 0.9925 4352/6993 [=================>............] - ETA: 0s - loss: 0.0633 - accuracy: 0.9915 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0650 - accuracy: 0.9910 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0867 - accuracy: 0.9902 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1227 - accuracy: 0.9903 - val_loss: 1.4142 - val_accuracy: 0.9287 Epoch 386/500 128/6993 [..............................] - ETA: 0s - loss: 0.1746 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0830 - accuracy: 0.9944 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1123 - accuracy: 0.9933 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1009 - accuracy: 0.9934 3456/6993 [=============>................] - ETA: 0s - loss: 0.1100 - accuracy: 0.9936 4352/6993 [=================>............] - ETA: 0s - loss: 0.0972 - accuracy: 0.9926 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1131 - accuracy: 0.9926 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1006 - accuracy: 0.9929 6912/6993 [============================>.] - ETA: 0s - loss: 0.0964 - accuracy: 0.9922 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1067 - accuracy: 0.9920 - val_loss: 1.3753 - val_accuracy: 0.9368 Epoch 387/500 128/6993 [..............................] - ETA: 0s - loss: 0.0225 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0506 - accuracy: 0.9902 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1249 - accuracy: 0.9885 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1139 - accuracy: 0.9890 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0961 - accuracy: 0.9900 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0857 - accuracy: 0.9902 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0907 - accuracy: 0.9900 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0880 - accuracy: 0.9904 6784/6993 [============================>.] - ETA: 0s - loss: 0.0822 - accuracy: 0.9909 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0852 - accuracy: 0.9906 - val_loss: 1.4850 - val_accuracy: 0.9338 Epoch 388/500 128/6993 [..............................] - ETA: 0s - loss: 0.0343 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0463 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0439 - accuracy: 0.9922 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0469 - accuracy: 0.9899 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0692 - accuracy: 0.9888 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0700 - accuracy: 0.9879 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0676 - accuracy: 0.9884 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0735 - accuracy: 0.9884 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0792 - accuracy: 0.9880 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0761 - accuracy: 0.9880 - val_loss: 1.3294 - val_accuracy: 0.9368 Epoch 389/500 128/6993 [..............................] - ETA: 0s - loss: 2.2546e-04 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0456 - accuracy: 0.9902 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0469 - accuracy: 0.9905 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0803 - accuracy: 0.9892 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0825 - accuracy: 0.9891 4352/6993 [=================>............] - ETA: 0s - loss: 0.0849 - accuracy: 0.9894 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0766 - accuracy: 0.9901 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0777 - accuracy: 0.9904 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0897 - accuracy: 0.9894 - val_loss: 1.4087 - val_accuracy: 0.9323 Epoch 390/500 128/6993 [..............................] - ETA: 0s - loss: 0.1859 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1099 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0667 - accuracy: 0.9898 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1562 - accuracy: 0.9870 3200/6993 [============>.................] - ETA: 0s - loss: 0.1667 - accuracy: 0.9866 3968/6993 [================>.............] - ETA: 0s - loss: 0.1399 - accuracy: 0.9882 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1226 - accuracy: 0.9892 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1097 - accuracy: 0.9895 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1002 - accuracy: 0.9905 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0993 - accuracy: 0.9901 - val_loss: 1.3271 - val_accuracy: 0.9343 Epoch 391/500 128/6993 [..............................] - ETA: 0s - loss: 0.0104 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0503 - accuracy: 0.9902 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0818 - accuracy: 0.9894 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0694 - accuracy: 0.9898 3456/6993 [=============>................] - ETA: 0s - loss: 0.1201 - accuracy: 0.9890 4352/6993 [=================>............] - ETA: 0s - loss: 0.1063 - accuracy: 0.9897 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1116 - accuracy: 0.9893 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1010 - accuracy: 0.9898 6784/6993 [============================>.] - ETA: 0s - loss: 0.0897 - accuracy: 0.9906 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0873 - accuracy: 0.9908 - val_loss: 1.4981 - val_accuracy: 0.9333 Epoch 392/500 128/6993 [..............................] - ETA: 0s - loss: 0.0206 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1669 - accuracy: 0.9933 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1033 - accuracy: 0.9939 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1027 - accuracy: 0.9934 3200/6993 [============>.................] - ETA: 0s - loss: 0.1361 - accuracy: 0.9925 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1184 - accuracy: 0.9927 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1049 - accuracy: 0.9926 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0985 - accuracy: 0.9924 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0938 - accuracy: 0.9924 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0906 - accuracy: 0.9920 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0892 - accuracy: 0.9920 - val_loss: 1.5861 - val_accuracy: 0.9312 Epoch 393/500 128/6993 [..............................] - ETA: 0s - loss: 0.1115 - accuracy: 0.9609 640/6993 [=>............................] - ETA: 0s - loss: 0.0878 - accuracy: 0.9906 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0673 - accuracy: 0.9908 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1254 - accuracy: 0.9902 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1072 - accuracy: 0.9903 3456/6993 [=============>................] - ETA: 0s - loss: 0.1029 - accuracy: 0.9902 4096/6993 [================>.............] - ETA: 0s - loss: 0.1498 - accuracy: 0.9893 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1443 - accuracy: 0.9885 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1400 - accuracy: 0.9879 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1478 - accuracy: 0.9881 6993/6993 [==============================] - 1s 95us/sample - loss: 0.1407 - accuracy: 0.9881 - val_loss: 1.3058 - val_accuracy: 0.9363 Epoch 394/500 128/6993 [..............................] - ETA: 0s - loss: 0.0182 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2724 - accuracy: 0.9863 1792/6993 [======>.......................] - ETA: 0s - loss: 0.3001 - accuracy: 0.9877 2560/6993 [=========>....................] - ETA: 0s - loss: 0.2331 - accuracy: 0.9871 3328/6993 [=============>................] - ETA: 0s - loss: 0.1888 - accuracy: 0.9886 4096/6993 [================>.............] - ETA: 0s - loss: 0.1622 - accuracy: 0.9902 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1415 - accuracy: 0.9901 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1447 - accuracy: 0.9905 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1291 - accuracy: 0.9899 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1290 - accuracy: 0.9897 - val_loss: 1.4819 - val_accuracy: 0.9333 Epoch 395/500 128/6993 [..............................] - ETA: 0s - loss: 0.2209 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.1087 - accuracy: 0.9844 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1391 - accuracy: 0.9850 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1213 - accuracy: 0.9868 3328/6993 [=============>................] - ETA: 0s - loss: 0.1145 - accuracy: 0.9877 4096/6993 [================>.............] - ETA: 0s - loss: 0.1312 - accuracy: 0.9883 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1521 - accuracy: 0.9883 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1381 - accuracy: 0.9893 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1263 - accuracy: 0.9894 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1194 - accuracy: 0.9893 - val_loss: 1.3643 - val_accuracy: 0.9292 Epoch 396/500 128/6993 [..............................] - ETA: 0s - loss: 0.0106 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0818 - accuracy: 0.9935 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0953 - accuracy: 0.9870 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1524 - accuracy: 0.9865 3200/6993 [============>.................] - ETA: 0s - loss: 0.1258 - accuracy: 0.9878 3968/6993 [================>.............] - ETA: 0s - loss: 0.1443 - accuracy: 0.9879 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1489 - accuracy: 0.9878 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1392 - accuracy: 0.9872 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1340 - accuracy: 0.9877 6784/6993 [============================>.] - ETA: 0s - loss: 0.1225 - accuracy: 0.9881 6993/6993 [==============================] - 1s 92us/sample - loss: 0.1281 - accuracy: 0.9878 - val_loss: 1.5273 - val_accuracy: 0.9343 Epoch 397/500 128/6993 [..............................] - ETA: 0s - loss: 0.1535 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0485 - accuracy: 0.9896 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0535 - accuracy: 0.9896 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0665 - accuracy: 0.9908 3072/6993 [============>.................] - ETA: 0s - loss: 0.0789 - accuracy: 0.9899 3968/6993 [================>.............] - ETA: 0s - loss: 0.0905 - accuracy: 0.9897 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0831 - accuracy: 0.9894 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1000 - accuracy: 0.9893 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0969 - accuracy: 0.9892 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0935 - accuracy: 0.9891 - val_loss: 1.6235 - val_accuracy: 0.9307 Epoch 398/500 128/6993 [..............................] - ETA: 0s - loss: 0.0572 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0610 - accuracy: 0.9912 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0583 - accuracy: 0.9888 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0605 - accuracy: 0.9895 3328/6993 [=============>................] - ETA: 0s - loss: 0.0752 - accuracy: 0.9895 4096/6993 [================>.............] - ETA: 0s - loss: 0.0707 - accuracy: 0.9888 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0673 - accuracy: 0.9887 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0621 - accuracy: 0.9889 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0661 - accuracy: 0.9890 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0668 - accuracy: 0.9884 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0640 - accuracy: 0.9890 - val_loss: 1.5192 - val_accuracy: 0.9368 Epoch 399/500 128/6993 [..............................] - ETA: 0s - loss: 0.0365 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0198 - accuracy: 0.9955 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0521 - accuracy: 0.9902 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1226 - accuracy: 0.9905 3072/6993 [============>.................] - ETA: 0s - loss: 0.1034 - accuracy: 0.9899 3968/6993 [================>.............] - ETA: 0s - loss: 0.1156 - accuracy: 0.9894 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1247 - accuracy: 0.9897 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1262 - accuracy: 0.9892 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1242 - accuracy: 0.9890 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1175 - accuracy: 0.9890 6784/6993 [============================>.] - ETA: 0s - loss: 0.1167 - accuracy: 0.9891 6993/6993 [==============================] - 1s 100us/sample - loss: 0.1149 - accuracy: 0.9891 - val_loss: 1.4253 - val_accuracy: 0.9368 Epoch 400/500 128/6993 [..............................] - ETA: 0s - loss: 0.0286 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.3527 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.2070 - accuracy: 0.9866 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1807 - accuracy: 0.9875 3328/6993 [=============>................] - ETA: 0s - loss: 0.1602 - accuracy: 0.9880 4096/6993 [================>.............] - ETA: 0s - loss: 0.1432 - accuracy: 0.9885 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1335 - accuracy: 0.9891 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1172 - accuracy: 0.9901 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1119 - accuracy: 0.9907 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1173 - accuracy: 0.9906 - val_loss: 1.3764 - val_accuracy: 0.9302 Epoch 401/500 128/6993 [..............................] - ETA: 0s - loss: 0.0087 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0831 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0792 - accuracy: 0.9922 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0765 - accuracy: 0.9927 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1339 - accuracy: 0.9911 3328/6993 [=============>................] - ETA: 0s - loss: 0.1157 - accuracy: 0.9904 3968/6993 [================>.............] - ETA: 0s - loss: 0.1229 - accuracy: 0.9899 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1141 - accuracy: 0.9891 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1100 - accuracy: 0.9891 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1153 - accuracy: 0.9891 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1078 - accuracy: 0.9892 6993/6993 [==============================] - 1s 105us/sample - loss: 0.0998 - accuracy: 0.9898 - val_loss: 1.3006 - val_accuracy: 0.9312 Epoch 402/500 128/6993 [..............................] - ETA: 0s - loss: 0.0014 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0237 - accuracy: 0.9933 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0755 - accuracy: 0.9905 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0781 - accuracy: 0.9906 3200/6993 [============>.................] - ETA: 0s - loss: 0.0738 - accuracy: 0.9906 3968/6993 [================>.............] - ETA: 0s - loss: 0.0765 - accuracy: 0.9889 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1278 - accuracy: 0.9886 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1238 - accuracy: 0.9883 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1236 - accuracy: 0.9880 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1302 - accuracy: 0.9881 6993/6993 [==============================] - 1s 87us/sample - loss: 0.1432 - accuracy: 0.9878 - val_loss: 1.2487 - val_accuracy: 0.9333 Epoch 403/500 128/6993 [..............................] - ETA: 0s - loss: 0.0408 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0786 - accuracy: 0.9883 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1240 - accuracy: 0.9896 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1103 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1056 - accuracy: 0.9881 3328/6993 [=============>................] - ETA: 0s - loss: 0.0900 - accuracy: 0.9892 3968/6993 [================>.............] - ETA: 0s - loss: 0.0781 - accuracy: 0.9899 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0759 - accuracy: 0.9911 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0706 - accuracy: 0.9907 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0890 - accuracy: 0.9908 6784/6993 [============================>.] - ETA: 0s - loss: 0.0831 - accuracy: 0.9909 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0834 - accuracy: 0.9908 - val_loss: 1.5340 - val_accuracy: 0.9312 Epoch 404/500 128/6993 [..............................] - ETA: 0s - loss: 2.7367e-04 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0745 - accuracy: 0.9933 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0917 - accuracy: 0.9916 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0640 - accuracy: 0.9940 3456/6993 [=============>................] - ETA: 0s - loss: 0.0556 - accuracy: 0.9939 4224/6993 [=================>............] - ETA: 0s - loss: 0.0486 - accuracy: 0.9938 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0442 - accuracy: 0.9939 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0592 - accuracy: 0.9935 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0605 - accuracy: 0.9933 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0826 - accuracy: 0.9923 - val_loss: 1.5907 - val_accuracy: 0.9338 Epoch 405/500 128/6993 [..............................] - ETA: 0s - loss: 0.0143 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1186 - accuracy: 0.9866 1536/6993 [=====>........................] - ETA: 0s - loss: 0.2190 - accuracy: 0.9863 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1976 - accuracy: 0.9887 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1741 - accuracy: 0.9885 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1498 - accuracy: 0.9884 4224/6993 [=================>............] - ETA: 0s - loss: 0.1463 - accuracy: 0.9886 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1296 - accuracy: 0.9893 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1294 - accuracy: 0.9895 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1243 - accuracy: 0.9900 6784/6993 [============================>.] - ETA: 0s - loss: 0.1205 - accuracy: 0.9901 6993/6993 [==============================] - 1s 101us/sample - loss: 0.1219 - accuracy: 0.9898 - val_loss: 1.2676 - val_accuracy: 0.9328 Epoch 406/500 128/6993 [..............................] - ETA: 0s - loss: 0.0021 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0493 - accuracy: 0.9944 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0746 - accuracy: 0.9928 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0706 - accuracy: 0.9926 3328/6993 [=============>................] - ETA: 0s - loss: 0.0796 - accuracy: 0.9913 4096/6993 [================>.............] - ETA: 0s - loss: 0.0885 - accuracy: 0.9905 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0787 - accuracy: 0.9899 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0747 - accuracy: 0.9899 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0755 - accuracy: 0.9894 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0714 - accuracy: 0.9898 - val_loss: 1.5493 - val_accuracy: 0.9317 Epoch 407/500 128/6993 [..............................] - ETA: 0s - loss: 0.0130 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.1739 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1215 - accuracy: 0.9922 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0911 - accuracy: 0.9922 3200/6993 [============>.................] - ETA: 0s - loss: 0.1504 - accuracy: 0.9916 4096/6993 [================>.............] - ETA: 0s - loss: 0.1266 - accuracy: 0.9905 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1185 - accuracy: 0.9902 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1118 - accuracy: 0.9900 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1038 - accuracy: 0.9896 6993/6993 [==============================] - 1s 79us/sample - loss: 0.1027 - accuracy: 0.9898 - val_loss: 1.2808 - val_accuracy: 0.9358 Epoch 408/500 128/6993 [..............................] - ETA: 0s - loss: 0.0300 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0701 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1231 - accuracy: 0.9905 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0954 - accuracy: 0.9902 3456/6993 [=============>................] - ETA: 0s - loss: 0.1212 - accuracy: 0.9884 4352/6993 [=================>............] - ETA: 0s - loss: 0.1221 - accuracy: 0.9878 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1119 - accuracy: 0.9881 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1119 - accuracy: 0.9885 6784/6993 [============================>.] - ETA: 0s - loss: 0.1167 - accuracy: 0.9882 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1148 - accuracy: 0.9883 - val_loss: 1.2430 - val_accuracy: 0.9348 Epoch 409/500 128/6993 [..............................] - ETA: 0s - loss: 0.0046 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1399 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1030 - accuracy: 0.9872 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1357 - accuracy: 0.9888 3456/6993 [=============>................] - ETA: 0s - loss: 0.1348 - accuracy: 0.9899 4352/6993 [=================>............] - ETA: 0s - loss: 0.1095 - accuracy: 0.9913 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0986 - accuracy: 0.9912 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1013 - accuracy: 0.9902 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0969 - accuracy: 0.9907 - val_loss: 1.2110 - val_accuracy: 0.9307 Epoch 410/500 128/6993 [..............................] - ETA: 0s - loss: 0.0973 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.2127 - accuracy: 0.9821 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1314 - accuracy: 0.9862 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1610 - accuracy: 0.9874 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1627 - accuracy: 0.9874 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1613 - accuracy: 0.9874 4224/6993 [=================>............] - ETA: 0s - loss: 0.1817 - accuracy: 0.9877 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1751 - accuracy: 0.9881 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1585 - accuracy: 0.9880 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1546 - accuracy: 0.9884 6784/6993 [============================>.] - ETA: 0s - loss: 0.1488 - accuracy: 0.9886 6993/6993 [==============================] - 1s 98us/sample - loss: 0.1473 - accuracy: 0.9887 - val_loss: 1.5286 - val_accuracy: 0.9302 Epoch 411/500 128/6993 [..............................] - ETA: 0s - loss: 0.0370 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.2482 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.2058 - accuracy: 0.9886 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1694 - accuracy: 0.9881 3200/6993 [============>.................] - ETA: 0s - loss: 0.1378 - accuracy: 0.9884 3968/6993 [================>.............] - ETA: 0s - loss: 0.1504 - accuracy: 0.9877 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1344 - accuracy: 0.9871 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1270 - accuracy: 0.9879 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1144 - accuracy: 0.9888 6912/6993 [============================>.] - ETA: 0s - loss: 0.1083 - accuracy: 0.9889 6993/6993 [==============================] - 1s 89us/sample - loss: 0.1090 - accuracy: 0.9887 - val_loss: 1.6269 - val_accuracy: 0.9328 Epoch 412/500 128/6993 [..............................] - ETA: 0s - loss: 0.0195 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0853 - accuracy: 0.9873 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0956 - accuracy: 0.9877 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0895 - accuracy: 0.9888 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1166 - accuracy: 0.9874 4352/6993 [=================>............] - ETA: 0s - loss: 0.1100 - accuracy: 0.9885 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0982 - accuracy: 0.9889 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0996 - accuracy: 0.9885 6912/6993 [============================>.] - ETA: 0s - loss: 0.1056 - accuracy: 0.9887 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1044 - accuracy: 0.9888 - val_loss: 1.4998 - val_accuracy: 0.9242 Epoch 413/500 128/6993 [..............................] - ETA: 0s - loss: 0.0220 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0983 - accuracy: 0.9912 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0967 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1088 - accuracy: 0.9900 3456/6993 [=============>................] - ETA: 0s - loss: 0.0928 - accuracy: 0.9896 4352/6993 [=================>............] - ETA: 0s - loss: 0.0820 - accuracy: 0.9894 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0961 - accuracy: 0.9891 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1465 - accuracy: 0.9887 6784/6993 [============================>.] - ETA: 0s - loss: 0.1530 - accuracy: 0.9884 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1489 - accuracy: 0.9884 - val_loss: 1.3614 - val_accuracy: 0.9323 Epoch 414/500 128/6993 [..............................] - ETA: 0s - loss: 0.0192 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1117 - accuracy: 0.9922 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0805 - accuracy: 0.9922 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0886 - accuracy: 0.9922 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0736 - accuracy: 0.9932 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0885 - accuracy: 0.9922 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0848 - accuracy: 0.9917 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0760 - accuracy: 0.9914 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0740 - accuracy: 0.9915 6784/6993 [============================>.] - ETA: 0s - loss: 0.0679 - accuracy: 0.9920 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0660 - accuracy: 0.9921 - val_loss: 1.5035 - val_accuracy: 0.9328 Epoch 415/500 128/6993 [..............................] - ETA: 0s - loss: 0.0613 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0307 - accuracy: 0.9955 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0235 - accuracy: 0.9952 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1948 - accuracy: 0.9922 3072/6993 [============>.................] - ETA: 0s - loss: 0.1589 - accuracy: 0.9925 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1311 - accuracy: 0.9930 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1681 - accuracy: 0.9922 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1564 - accuracy: 0.9914 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1415 - accuracy: 0.9910 6993/6993 [==============================] - 1s 87us/sample - loss: 0.1262 - accuracy: 0.9918 - val_loss: 1.4912 - val_accuracy: 0.9353 Epoch 416/500 128/6993 [..............................] - ETA: 0s - loss: 0.1578 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0531 - accuracy: 0.9944 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0426 - accuracy: 0.9922 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0358 - accuracy: 0.9930 3200/6993 [============>.................] - ETA: 0s - loss: 0.0794 - accuracy: 0.9919 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0758 - accuracy: 0.9922 4224/6993 [=================>............] - ETA: 0s - loss: 0.1081 - accuracy: 0.9908 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1110 - accuracy: 0.9905 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1256 - accuracy: 0.9905 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1168 - accuracy: 0.9907 6784/6993 [============================>.] - ETA: 0s - loss: 0.1119 - accuracy: 0.9904 6993/6993 [==============================] - 1s 94us/sample - loss: 0.1274 - accuracy: 0.9904 - val_loss: 1.2104 - val_accuracy: 0.9368 Epoch 417/500 128/6993 [..............................] - ETA: 0s - loss: 0.0034 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.1081 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1542 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1513 - accuracy: 0.9877 3456/6993 [=============>................] - ETA: 0s - loss: 0.1454 - accuracy: 0.9876 4352/6993 [=================>............] - ETA: 0s - loss: 0.1520 - accuracy: 0.9878 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1388 - accuracy: 0.9881 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1334 - accuracy: 0.9870 6912/6993 [============================>.] - ETA: 0s - loss: 0.1184 - accuracy: 0.9880 6993/6993 [==============================] - 1s 79us/sample - loss: 0.1172 - accuracy: 0.9881 - val_loss: 1.1330 - val_accuracy: 0.9378 Epoch 418/500 128/6993 [..............................] - ETA: 0s - loss: 0.0720 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1292 - accuracy: 0.9911 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1285 - accuracy: 0.9889 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1215 - accuracy: 0.9873 3072/6993 [============>.................] - ETA: 0s - loss: 0.1126 - accuracy: 0.9873 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1294 - accuracy: 0.9873 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1218 - accuracy: 0.9877 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1170 - accuracy: 0.9877 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1185 - accuracy: 0.9882 6993/6993 [==============================] - 1s 82us/sample - loss: 0.1173 - accuracy: 0.9877 - val_loss: 1.1653 - val_accuracy: 0.9328 Epoch 419/500 128/6993 [..............................] - ETA: 0s - loss: 0.0093 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0543 - accuracy: 0.9888 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0538 - accuracy: 0.9879 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1433 - accuracy: 0.9859 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1238 - accuracy: 0.9855 3328/6993 [=============>................] - ETA: 0s - loss: 0.1121 - accuracy: 0.9871 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1040 - accuracy: 0.9875 4352/6993 [=================>............] - ETA: 0s - loss: 0.0979 - accuracy: 0.9871 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0943 - accuracy: 0.9872 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0949 - accuracy: 0.9863 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1057 - accuracy: 0.9871 6993/6993 [==============================] - 1s 95us/sample - loss: 0.1088 - accuracy: 0.9873 - val_loss: 1.1631 - val_accuracy: 0.9277 Epoch 420/500 128/6993 [..............................] - ETA: 0s - loss: 0.0086 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0246 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0950 - accuracy: 0.9893 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0747 - accuracy: 0.9902 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0696 - accuracy: 0.9911 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0932 - accuracy: 0.9908 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1247 - accuracy: 0.9904 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1188 - accuracy: 0.9900 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1184 - accuracy: 0.9901 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1069 - accuracy: 0.9904 - val_loss: 1.3204 - val_accuracy: 0.9333 Epoch 421/500 128/6993 [..............................] - ETA: 0s - loss: 0.0096 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0865 - accuracy: 0.9971 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0639 - accuracy: 0.9944 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9933 3456/6993 [=============>................] - ETA: 0s - loss: 0.1270 - accuracy: 0.9919 4352/6993 [=================>............] - ETA: 0s - loss: 0.1135 - accuracy: 0.9917 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1028 - accuracy: 0.9909 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1126 - accuracy: 0.9910 6912/6993 [============================>.] - ETA: 0s - loss: 0.1107 - accuracy: 0.9905 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1111 - accuracy: 0.9903 - val_loss: 1.1850 - val_accuracy: 0.9297 Epoch 422/500 128/6993 [..............................] - ETA: 0s - loss: 0.2399 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0695 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1823 - accuracy: 0.9888 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1930 - accuracy: 0.9863 3456/6993 [=============>................] - ETA: 0s - loss: 0.1511 - accuracy: 0.9890 4352/6993 [=================>............] - ETA: 0s - loss: 0.1332 - accuracy: 0.9899 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1309 - accuracy: 0.9895 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1345 - accuracy: 0.9889 6912/6993 [============================>.] - ETA: 0s - loss: 0.1296 - accuracy: 0.9887 6993/6993 [==============================] - 1s 79us/sample - loss: 0.1281 - accuracy: 0.9888 - val_loss: 1.1737 - val_accuracy: 0.9343 Epoch 423/500 128/6993 [..............................] - ETA: 0s - loss: 0.0201 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0084 - accuracy: 0.9969 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0105 - accuracy: 0.9950 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0147 - accuracy: 0.9941 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0203 - accuracy: 0.9933 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0203 - accuracy: 0.9939 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0480 - accuracy: 0.9931 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0557 - accuracy: 0.9927 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0534 - accuracy: 0.9923 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0560 - accuracy: 0.9923 - val_loss: 1.3592 - val_accuracy: 0.9323 Epoch 424/500 128/6993 [..............................] - ETA: 0s - loss: 0.0011 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0887 - accuracy: 0.9941 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0956 - accuracy: 0.9911 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1015 - accuracy: 0.9914 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0851 - accuracy: 0.9925 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0817 - accuracy: 0.9922 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0806 - accuracy: 0.9920 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0770 - accuracy: 0.9912 6784/6993 [============================>.] - ETA: 0s - loss: 0.0796 - accuracy: 0.9913 6993/6993 [==============================] - 1s 77us/sample - loss: 0.0801 - accuracy: 0.9913 - val_loss: 1.4204 - val_accuracy: 0.9282 Epoch 425/500 128/6993 [..............................] - ETA: 0s - loss: 0.1273 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1197 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1234 - accuracy: 0.9910 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1043 - accuracy: 0.9902 3328/6993 [=============>................] - ETA: 0s - loss: 0.2678 - accuracy: 0.9907 4224/6993 [=================>............] - ETA: 0s - loss: 0.2286 - accuracy: 0.9893 4992/6993 [====================>.........] - ETA: 0s - loss: 0.2136 - accuracy: 0.9886 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1910 - accuracy: 0.9885 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1795 - accuracy: 0.9890 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1721 - accuracy: 0.9893 - val_loss: 1.3979 - val_accuracy: 0.9317 Epoch 426/500 128/6993 [..............................] - ETA: 0s - loss: 0.0233 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2024 - accuracy: 0.9941 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1385 - accuracy: 0.9927 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1033 - accuracy: 0.9926 3456/6993 [=============>................] - ETA: 0s - loss: 0.0984 - accuracy: 0.9928 4352/6993 [=================>............] - ETA: 0s - loss: 0.0877 - accuracy: 0.9931 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0857 - accuracy: 0.9920 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0976 - accuracy: 0.9920 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0897 - accuracy: 0.9923 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0874 - accuracy: 0.9921 - val_loss: 1.6097 - val_accuracy: 0.9312 Epoch 427/500 128/6993 [..............................] - ETA: 0s - loss: 3.3035e-04 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2553 - accuracy: 0.9893 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1892 - accuracy: 0.9894 2560/6993 [=========>....................] - ETA: 0s - loss: 0.2282 - accuracy: 0.9855 3456/6993 [=============>................] - ETA: 0s - loss: 0.1796 - accuracy: 0.9873 4224/6993 [=================>............] - ETA: 0s - loss: 0.1646 - accuracy: 0.9875 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1697 - accuracy: 0.9879 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1502 - accuracy: 0.9888 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1366 - accuracy: 0.9893 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1307 - accuracy: 0.9896 - val_loss: 1.5958 - val_accuracy: 0.9317 Epoch 428/500 128/6993 [..............................] - ETA: 0s - loss: 0.0841 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0518 - accuracy: 0.9961 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0481 - accuracy: 0.9940 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0447 - accuracy: 0.9930 3200/6993 [============>.................] - ETA: 0s - loss: 0.0571 - accuracy: 0.9912 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0884 - accuracy: 0.9904 4352/6993 [=================>............] - ETA: 0s - loss: 0.0994 - accuracy: 0.9910 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1295 - accuracy: 0.9904 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1242 - accuracy: 0.9892 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1211 - accuracy: 0.9895 6993/6993 [==============================] - 1s 92us/sample - loss: 0.1143 - accuracy: 0.9900 - val_loss: 1.9605 - val_accuracy: 0.9257 Epoch 429/500 128/6993 [..............................] - ETA: 0s - loss: 0.0472 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1480 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1303 - accuracy: 0.9894 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1610 - accuracy: 0.9879 3328/6993 [=============>................] - ETA: 0s - loss: 0.1491 - accuracy: 0.9874 4096/6993 [================>.............] - ETA: 0s - loss: 0.1284 - accuracy: 0.9883 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1109 - accuracy: 0.9894 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1024 - accuracy: 0.9898 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0988 - accuracy: 0.9902 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0945 - accuracy: 0.9907 - val_loss: 1.7249 - val_accuracy: 0.9272 Epoch 430/500 128/6993 [..............................] - ETA: 0s - loss: 0.0020 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0118 - accuracy: 0.9967 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0208 - accuracy: 0.9933 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0265 - accuracy: 0.9926 3328/6993 [=============>................] - ETA: 0s - loss: 0.0681 - accuracy: 0.9922 4224/6993 [=================>............] - ETA: 0s - loss: 0.1380 - accuracy: 0.9915 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1583 - accuracy: 0.9918 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1524 - accuracy: 0.9911 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1570 - accuracy: 0.9909 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1546 - accuracy: 0.9898 - val_loss: 1.6448 - val_accuracy: 0.9221 Epoch 431/500 128/6993 [..............................] - ETA: 0s - loss: 0.0123 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.2100 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1568 - accuracy: 0.9872 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1216 - accuracy: 0.9876 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1500 - accuracy: 0.9881 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1418 - accuracy: 0.9883 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1248 - accuracy: 0.9885 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1110 - accuracy: 0.9889 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1069 - accuracy: 0.9886 6993/6993 [==============================] - 1s 79us/sample - loss: 0.1011 - accuracy: 0.9891 - val_loss: 1.6242 - val_accuracy: 0.9237 Epoch 432/500 128/6993 [..............................] - ETA: 0s - loss: 0.0674 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0257 - accuracy: 0.9951 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0235 - accuracy: 0.9955 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0232 - accuracy: 0.9957 3072/6993 [============>.................] - ETA: 0s - loss: 0.0643 - accuracy: 0.9932 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0543 - accuracy: 0.9940 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0499 - accuracy: 0.9942 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0525 - accuracy: 0.9939 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0492 - accuracy: 0.9937 6912/6993 [============================>.] - ETA: 0s - loss: 0.0506 - accuracy: 0.9935 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0508 - accuracy: 0.9934 - val_loss: 2.2387 - val_accuracy: 0.9262 Epoch 433/500 128/6993 [..............................] - ETA: 0s - loss: 0.1434 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.2784 - accuracy: 0.9855 1536/6993 [=====>........................] - ETA: 0s - loss: 0.2123 - accuracy: 0.9876 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1626 - accuracy: 0.9900 3200/6993 [============>.................] - ETA: 0s - loss: 0.1411 - accuracy: 0.9891 4096/6993 [================>.............] - ETA: 0s - loss: 0.1303 - accuracy: 0.9897 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1278 - accuracy: 0.9899 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1369 - accuracy: 0.9901 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1239 - accuracy: 0.9907 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1170 - accuracy: 0.9908 - val_loss: 1.7481 - val_accuracy: 0.9277 Epoch 434/500 128/6993 [..............................] - ETA: 0s - loss: 0.2775 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.4197 - accuracy: 0.9857 1536/6993 [=====>........................] - ETA: 0s - loss: 0.2175 - accuracy: 0.9909 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1837 - accuracy: 0.9913 3200/6993 [============>.................] - ETA: 0s - loss: 0.1993 - accuracy: 0.9912 4096/6993 [================>.............] - ETA: 0s - loss: 0.1576 - accuracy: 0.9927 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1353 - accuracy: 0.9928 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1245 - accuracy: 0.9934 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1212 - accuracy: 0.9932 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1299 - accuracy: 0.9930 - val_loss: 2.1146 - val_accuracy: 0.9272 Epoch 435/500 128/6993 [..............................] - ETA: 0s - loss: 0.1561 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0679 - accuracy: 0.9948 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0485 - accuracy: 0.9958 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0647 - accuracy: 0.9947 3328/6993 [=============>................] - ETA: 0s - loss: 0.0505 - accuracy: 0.9952 4224/6993 [=================>............] - ETA: 0s - loss: 0.0867 - accuracy: 0.9936 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0797 - accuracy: 0.9934 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0795 - accuracy: 0.9929 6784/6993 [============================>.] - ETA: 0s - loss: 0.0813 - accuracy: 0.9917 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0791 - accuracy: 0.9918 - val_loss: 1.7350 - val_accuracy: 0.9257 Epoch 436/500 128/6993 [..............................] - ETA: 0s - loss: 0.0011 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0857 - accuracy: 0.9902 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0916 - accuracy: 0.9906 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0798 - accuracy: 0.9911 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0879 - accuracy: 0.9891 4352/6993 [=================>............] - ETA: 0s - loss: 0.0809 - accuracy: 0.9892 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0944 - accuracy: 0.9891 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0890 - accuracy: 0.9895 6912/6993 [============================>.] - ETA: 0s - loss: 0.0896 - accuracy: 0.9897 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0896 - accuracy: 0.9896 - val_loss: 1.5844 - val_accuracy: 0.9297 Epoch 437/500 128/6993 [..............................] - ETA: 0s - loss: 0.0197 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 1.2511 - accuracy: 0.9902 1920/6993 [=======>......................] - ETA: 0s - loss: 0.6957 - accuracy: 0.9906 2688/6993 [==========>...................] - ETA: 0s - loss: 0.5319 - accuracy: 0.9892 3584/6993 [==============>...............] - ETA: 0s - loss: 0.4441 - accuracy: 0.9894 4480/6993 [==================>...........] - ETA: 0s - loss: 0.3742 - accuracy: 0.9884 5248/6993 [=====================>........] - ETA: 0s - loss: 0.3722 - accuracy: 0.9872 6016/6993 [========================>.....] - ETA: 0s - loss: 0.3378 - accuracy: 0.9880 6528/6993 [===========================>..] - ETA: 0s - loss: 0.3171 - accuracy: 0.9879 6993/6993 [==============================] - 1s 84us/sample - loss: 0.2986 - accuracy: 0.9877 - val_loss: 1.5155 - val_accuracy: 0.9242 Epoch 438/500 128/6993 [..............................] - ETA: 0s - loss: 0.1247 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0536 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0609 - accuracy: 0.9915 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0480 - accuracy: 0.9907 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0503 - accuracy: 0.9892 3328/6993 [=============>................] - ETA: 0s - loss: 0.0466 - accuracy: 0.9901 3968/6993 [================>.............] - ETA: 0s - loss: 0.0592 - accuracy: 0.9894 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0606 - accuracy: 0.9889 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0552 - accuracy: 0.9894 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0575 - accuracy: 0.9901 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0592 - accuracy: 0.9904 - val_loss: 1.9004 - val_accuracy: 0.9267 Epoch 439/500 128/6993 [..............................] - ETA: 0s - loss: 0.0082 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0567 - accuracy: 0.9900 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0511 - accuracy: 0.9900 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0927 - accuracy: 0.9898 3456/6993 [=============>................] - ETA: 0s - loss: 0.1533 - accuracy: 0.9887 4096/6993 [================>.............] - ETA: 0s - loss: 0.1506 - accuracy: 0.9880 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1579 - accuracy: 0.9880 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1522 - accuracy: 0.9887 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1518 - accuracy: 0.9888 6912/6993 [============================>.] - ETA: 0s - loss: 0.1407 - accuracy: 0.9890 6993/6993 [==============================] - 1s 84us/sample - loss: 0.1393 - accuracy: 0.9890 - val_loss: 1.6576 - val_accuracy: 0.9287 Epoch 440/500 128/6993 [..............................] - ETA: 0s - loss: 0.0325 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0444 - accuracy: 0.9922 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0336 - accuracy: 0.9909 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0314 - accuracy: 0.9926 3200/6993 [============>.................] - ETA: 0s - loss: 0.0765 - accuracy: 0.9937 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0746 - accuracy: 0.9937 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0656 - accuracy: 0.9933 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0731 - accuracy: 0.9927 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0738 - accuracy: 0.9927 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0708 - accuracy: 0.9927 - val_loss: 1.7410 - val_accuracy: 0.9317 Epoch 441/500 128/6993 [..............................] - ETA: 0s - loss: 2.8403e-05 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.1253 - accuracy: 0.9961 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1893 - accuracy: 0.9916 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1719 - accuracy: 0.9910 3200/6993 [============>.................] - ETA: 0s - loss: 0.1596 - accuracy: 0.9903 3968/6993 [================>.............] - ETA: 0s - loss: 0.1688 - accuracy: 0.9887 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1516 - accuracy: 0.9887 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1522 - accuracy: 0.9890 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1396 - accuracy: 0.9891 6784/6993 [============================>.] - ETA: 0s - loss: 0.1330 - accuracy: 0.9894 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1313 - accuracy: 0.9896 - val_loss: 1.7039 - val_accuracy: 0.9307 Epoch 442/500 128/6993 [..............................] - ETA: 0s - loss: 0.0474 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0198 - accuracy: 0.9932 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0672 - accuracy: 0.9917 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0563 - accuracy: 0.9926 3328/6993 [=============>................] - ETA: 0s - loss: 0.1076 - accuracy: 0.9916 4224/6993 [=================>............] - ETA: 0s - loss: 0.1208 - accuracy: 0.9903 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1365 - accuracy: 0.9904 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1447 - accuracy: 0.9900 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1370 - accuracy: 0.9902 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1406 - accuracy: 0.9897 - val_loss: 1.7305 - val_accuracy: 0.9272 Epoch 443/500 128/6993 [..............................] - ETA: 0s - loss: 0.0668 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0835 - accuracy: 0.9911 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0508 - accuracy: 0.9940 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0566 - accuracy: 0.9937 3456/6993 [=============>................] - ETA: 0s - loss: 0.0472 - accuracy: 0.9939 4224/6993 [=================>............] - ETA: 0s - loss: 0.0580 - accuracy: 0.9924 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0878 - accuracy: 0.9916 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0867 - accuracy: 0.9915 6784/6993 [============================>.] - ETA: 0s - loss: 0.0981 - accuracy: 0.9903 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0971 - accuracy: 0.9901 - val_loss: 1.6041 - val_accuracy: 0.9277 Epoch 444/500 128/6993 [..............................] - ETA: 0s - loss: 0.5554 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1097 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0966 - accuracy: 0.9910 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0762 - accuracy: 0.9922 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0885 - accuracy: 0.9905 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1248 - accuracy: 0.9894 4224/6993 [=================>............] - ETA: 0s - loss: 0.1228 - accuracy: 0.9886 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1129 - accuracy: 0.9887 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1088 - accuracy: 0.9884 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1135 - accuracy: 0.9883 6784/6993 [============================>.] - ETA: 0s - loss: 0.1071 - accuracy: 0.9884 6993/6993 [==============================] - 1s 92us/sample - loss: 0.1066 - accuracy: 0.9883 - val_loss: 1.4280 - val_accuracy: 0.9277 Epoch 445/500 128/6993 [..............................] - ETA: 0s - loss: 0.0327 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.2158 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.2808 - accuracy: 0.9872 2048/6993 [=======>......................] - ETA: 0s - loss: 0.2159 - accuracy: 0.9897 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1733 - accuracy: 0.9888 3456/6993 [=============>................] - ETA: 0s - loss: 0.1601 - accuracy: 0.9890 4352/6993 [=================>............] - ETA: 0s - loss: 0.1692 - accuracy: 0.9887 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1692 - accuracy: 0.9891 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1621 - accuracy: 0.9890 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1567 - accuracy: 0.9893 6993/6993 [==============================] - 1s 84us/sample - loss: 0.1591 - accuracy: 0.9890 - val_loss: 1.5280 - val_accuracy: 0.9282 Epoch 446/500 128/6993 [..............................] - ETA: 0s - loss: 0.0033 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0253 - accuracy: 0.9935 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0820 - accuracy: 0.9901 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0752 - accuracy: 0.9902 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0726 - accuracy: 0.9911 3328/6993 [=============>................] - ETA: 0s - loss: 0.0704 - accuracy: 0.9919 3968/6993 [================>.............] - ETA: 0s - loss: 0.0657 - accuracy: 0.9919 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0801 - accuracy: 0.9905 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0795 - accuracy: 0.9903 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0759 - accuracy: 0.9895 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0795 - accuracy: 0.9891 6912/6993 [============================>.] - ETA: 0s - loss: 0.0785 - accuracy: 0.9889 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0831 - accuracy: 0.9888 - val_loss: 1.4351 - val_accuracy: 0.9388 Epoch 447/500 128/6993 [..............................] - ETA: 0s - loss: 0.0185 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1220 - accuracy: 0.9909 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0800 - accuracy: 0.9930 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0640 - accuracy: 0.9916 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0536 - accuracy: 0.9918 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0700 - accuracy: 0.9912 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1008 - accuracy: 0.9919 4224/6993 [=================>............] - ETA: 0s - loss: 0.1091 - accuracy: 0.9915 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1278 - accuracy: 0.9916 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1182 - accuracy: 0.9916 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1081 - accuracy: 0.9917 6784/6993 [============================>.] - ETA: 0s - loss: 0.1171 - accuracy: 0.9913 6993/6993 [==============================] - 1s 99us/sample - loss: 0.1176 - accuracy: 0.9914 - val_loss: 1.6446 - val_accuracy: 0.9302 Epoch 448/500 128/6993 [..............................] - ETA: 0s - loss: 0.1341 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0407 - accuracy: 0.9935 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0423 - accuracy: 0.9943 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0965 - accuracy: 0.9907 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0917 - accuracy: 0.9896 3328/6993 [=============>................] - ETA: 0s - loss: 0.0852 - accuracy: 0.9901 3968/6993 [================>.............] - ETA: 0s - loss: 0.0921 - accuracy: 0.9897 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1627 - accuracy: 0.9909 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1578 - accuracy: 0.9912 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1927 - accuracy: 0.9912 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1783 - accuracy: 0.9913 6993/6993 [==============================] - 1s 92us/sample - loss: 0.1721 - accuracy: 0.9911 - val_loss: 1.3933 - val_accuracy: 0.9363 Epoch 449/500 128/6993 [..............................] - ETA: 0s - loss: 0.0459 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0609 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1303 - accuracy: 0.9865 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1008 - accuracy: 0.9873 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1122 - accuracy: 0.9881 3328/6993 [=============>................] - ETA: 0s - loss: 0.0941 - accuracy: 0.9895 3968/6993 [================>.............] - ETA: 0s - loss: 0.0963 - accuracy: 0.9877 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0901 - accuracy: 0.9883 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0853 - accuracy: 0.9891 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0888 - accuracy: 0.9893 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0850 - accuracy: 0.9894 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0908 - accuracy: 0.9893 - val_loss: 1.4579 - val_accuracy: 0.9292 Epoch 450/500 128/6993 [..............................] - ETA: 0s - loss: 0.2441 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0707 - accuracy: 0.9909 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0502 - accuracy: 0.9930 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0669 - accuracy: 0.9917 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0696 - accuracy: 0.9901 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0864 - accuracy: 0.9908 3456/6993 [=============>................] - ETA: 0s - loss: 0.0803 - accuracy: 0.9905 4096/6993 [================>.............] - ETA: 0s - loss: 0.0790 - accuracy: 0.9907 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0994 - accuracy: 0.9907 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1076 - accuracy: 0.9896 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1077 - accuracy: 0.9897 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1078 - accuracy: 0.9889 6993/6993 [==============================] - 1s 99us/sample - loss: 0.1063 - accuracy: 0.9887 - val_loss: 1.5608 - val_accuracy: 0.9343 Epoch 451/500 128/6993 [..............................] - ETA: 0s - loss: 0.3758 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0918 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.2098 - accuracy: 0.9858 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1806 - accuracy: 0.9854 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1531 - accuracy: 0.9870 3328/6993 [=============>................] - ETA: 0s - loss: 0.1265 - accuracy: 0.9889 3968/6993 [================>.............] - ETA: 0s - loss: 0.1183 - accuracy: 0.9902 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1278 - accuracy: 0.9902 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1444 - accuracy: 0.9901 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1329 - accuracy: 0.9902 6784/6993 [============================>.] - ETA: 0s - loss: 0.1326 - accuracy: 0.9895 6993/6993 [==============================] - 1s 90us/sample - loss: 0.1313 - accuracy: 0.9897 - val_loss: 1.6331 - val_accuracy: 0.9328 Epoch 452/500 128/6993 [..............................] - ETA: 0s - loss: 0.0875 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1473 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0874 - accuracy: 0.9915 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0646 - accuracy: 0.9917 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0906 - accuracy: 0.9918 3328/6993 [=============>................] - ETA: 0s - loss: 0.1223 - accuracy: 0.9898 3968/6993 [================>.............] - ETA: 0s - loss: 0.1065 - accuracy: 0.9897 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0985 - accuracy: 0.9890 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0927 - accuracy: 0.9888 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0973 - accuracy: 0.9890 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0970 - accuracy: 0.9892 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0938 - accuracy: 0.9891 - val_loss: 1.6481 - val_accuracy: 0.9317 Epoch 453/500 128/6993 [..............................] - ETA: 0s - loss: 0.0646 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0827 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0742 - accuracy: 0.9879 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1062 - accuracy: 0.9893 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1126 - accuracy: 0.9892 3328/6993 [=============>................] - ETA: 0s - loss: 0.1086 - accuracy: 0.9889 3968/6993 [================>.............] - ETA: 0s - loss: 0.1249 - accuracy: 0.9889 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1185 - accuracy: 0.9891 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1106 - accuracy: 0.9889 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1244 - accuracy: 0.9885 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1382 - accuracy: 0.9876 6993/6993 [==============================] - 1s 94us/sample - loss: 0.1416 - accuracy: 0.9876 - val_loss: 1.7736 - val_accuracy: 0.9348 Epoch 454/500 128/6993 [..............................] - ETA: 0s - loss: 0.3560 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.1256 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0785 - accuracy: 0.9915 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1083 - accuracy: 0.9907 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0895 - accuracy: 0.9914 3328/6993 [=============>................] - ETA: 0s - loss: 0.1003 - accuracy: 0.9907 3968/6993 [================>.............] - ETA: 0s - loss: 0.1213 - accuracy: 0.9909 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1097 - accuracy: 0.9907 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1063 - accuracy: 0.9907 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1136 - accuracy: 0.9903 6912/6993 [============================>.] - ETA: 0s - loss: 0.1108 - accuracy: 0.9905 6993/6993 [==============================] - 1s 92us/sample - loss: 0.1096 - accuracy: 0.9906 - val_loss: 1.6955 - val_accuracy: 0.9343 Epoch 455/500 128/6993 [..............................] - ETA: 0s - loss: 0.0059 - accuracy: 1.0000 640/6993 [=>............................] - ETA: 0s - loss: 0.0783 - accuracy: 0.9906 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0746 - accuracy: 0.9905 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0806 - accuracy: 0.9911 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1348 - accuracy: 0.9898 3200/6993 [============>.................] - ETA: 0s - loss: 0.1476 - accuracy: 0.9900 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1294 - accuracy: 0.9906 4352/6993 [=================>............] - ETA: 0s - loss: 0.1148 - accuracy: 0.9906 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1451 - accuracy: 0.9906 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1761 - accuracy: 0.9901 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1717 - accuracy: 0.9892 6993/6993 [==============================] - 1s 99us/sample - loss: 0.1682 - accuracy: 0.9886 - val_loss: 1.4014 - val_accuracy: 0.9307 Epoch 456/500 128/6993 [..............................] - ETA: 0s - loss: 0.0696 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0651 - accuracy: 0.9935 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0515 - accuracy: 0.9936 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0995 - accuracy: 0.9932 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1008 - accuracy: 0.9918 3328/6993 [=============>................] - ETA: 0s - loss: 0.0950 - accuracy: 0.9898 3968/6993 [================>.............] - ETA: 0s - loss: 0.0886 - accuracy: 0.9907 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0940 - accuracy: 0.9905 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0893 - accuracy: 0.9907 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0959 - accuracy: 0.9903 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0899 - accuracy: 0.9910 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0853 - accuracy: 0.9913 - val_loss: 1.6952 - val_accuracy: 0.9343 Epoch 457/500 128/6993 [..............................] - ETA: 0s - loss: 0.0096 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0225 - accuracy: 0.9948 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0268 - accuracy: 0.9945 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0870 - accuracy: 0.9905 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0779 - accuracy: 0.9909 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0694 - accuracy: 0.9918 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0753 - accuracy: 0.9914 4224/6993 [=================>............] - ETA: 0s - loss: 0.0903 - accuracy: 0.9915 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0826 - accuracy: 0.9916 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0799 - accuracy: 0.9907 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0809 - accuracy: 0.9904 6784/6993 [============================>.] - ETA: 0s - loss: 0.0763 - accuracy: 0.9903 6993/6993 [==============================] - 1s 101us/sample - loss: 0.0775 - accuracy: 0.9903 - val_loss: 1.6549 - val_accuracy: 0.9287 Epoch 458/500 128/6993 [..............................] - ETA: 0s - loss: 0.0053 - accuracy: 1.0000 640/6993 [=>............................] - ETA: 0s - loss: 0.0412 - accuracy: 0.9922 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0632 - accuracy: 0.9861 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0505 - accuracy: 0.9880 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0588 - accuracy: 0.9867 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0558 - accuracy: 0.9874 3200/6993 [============>.................] - ETA: 0s - loss: 0.0529 - accuracy: 0.9884 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0601 - accuracy: 0.9890 4352/6993 [=================>............] - ETA: 0s - loss: 0.0688 - accuracy: 0.9894 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0677 - accuracy: 0.9898 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0733 - accuracy: 0.9897 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0677 - accuracy: 0.9903 6912/6993 [============================>.] - ETA: 0s - loss: 0.0986 - accuracy: 0.9896 6993/6993 [==============================] - 1s 105us/sample - loss: 0.0974 - accuracy: 0.9897 - val_loss: 1.6318 - val_accuracy: 0.9262 Epoch 459/500 128/6993 [..............................] - ETA: 0s - loss: 0.1040 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0730 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0848 - accuracy: 0.9879 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0719 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0570 - accuracy: 0.9903 3328/6993 [=============>................] - ETA: 0s - loss: 0.1640 - accuracy: 0.9889 3968/6993 [================>.............] - ETA: 0s - loss: 0.1400 - accuracy: 0.9899 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1298 - accuracy: 0.9891 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1198 - accuracy: 0.9897 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1056 - accuracy: 0.9909 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0958 - accuracy: 0.9916 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0941 - accuracy: 0.9916 - val_loss: 1.7254 - val_accuracy: 0.9317 Epoch 460/500 128/6993 [..............................] - ETA: 0s - loss: 0.0960 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0619 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0796 - accuracy: 0.9879 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0912 - accuracy: 0.9873 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0980 - accuracy: 0.9881 3328/6993 [=============>................] - ETA: 0s - loss: 0.1160 - accuracy: 0.9889 3968/6993 [================>.............] - ETA: 0s - loss: 0.1215 - accuracy: 0.9899 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1177 - accuracy: 0.9900 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1065 - accuracy: 0.9907 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1121 - accuracy: 0.9896 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1176 - accuracy: 0.9894 6993/6993 [==============================] - 1s 93us/sample - loss: 0.1118 - accuracy: 0.9897 - val_loss: 1.5496 - val_accuracy: 0.9302 Epoch 461/500 128/6993 [..............................] - ETA: 0s - loss: 0.0244 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0192 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0753 - accuracy: 0.9915 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0587 - accuracy: 0.9927 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0632 - accuracy: 0.9933 3456/6993 [=============>................] - ETA: 0s - loss: 0.0590 - accuracy: 0.9919 4224/6993 [=================>............] - ETA: 0s - loss: 0.0748 - accuracy: 0.9912 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0781 - accuracy: 0.9912 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0716 - accuracy: 0.9908 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0718 - accuracy: 0.9907 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0675 - accuracy: 0.9910 - val_loss: 1.7687 - val_accuracy: 0.9373 Epoch 462/500 128/6993 [..............................] - ETA: 0s - loss: 0.0996 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0736 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0683 - accuracy: 0.9872 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0680 - accuracy: 0.9874 3456/6993 [=============>................] - ETA: 0s - loss: 0.1081 - accuracy: 0.9878 4352/6993 [=================>............] - ETA: 0s - loss: 0.0976 - accuracy: 0.9890 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0845 - accuracy: 0.9902 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0877 - accuracy: 0.9905 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0790 - accuracy: 0.9910 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0792 - accuracy: 0.9908 - val_loss: 1.8190 - val_accuracy: 0.9297 Epoch 463/500 128/6993 [..............................] - ETA: 0s - loss: 0.0074 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2319 - accuracy: 0.9883 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1935 - accuracy: 0.9905 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1601 - accuracy: 0.9901 3072/6993 [============>.................] - ETA: 0s - loss: 0.1856 - accuracy: 0.9893 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1707 - accuracy: 0.9900 4224/6993 [=================>............] - ETA: 0s - loss: 0.1607 - accuracy: 0.9905 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1582 - accuracy: 0.9899 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1937 - accuracy: 0.9904 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1814 - accuracy: 0.9902 6784/6993 [============================>.] - ETA: 0s - loss: 0.1684 - accuracy: 0.9901 6993/6993 [==============================] - 1s 96us/sample - loss: 0.1643 - accuracy: 0.9903 - val_loss: 1.4276 - val_accuracy: 0.9323 Epoch 464/500 128/6993 [..............................] - ETA: 0s - loss: 0.0083 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0498 - accuracy: 0.9941 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0583 - accuracy: 0.9922 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0903 - accuracy: 0.9918 3456/6993 [=============>................] - ETA: 0s - loss: 0.0863 - accuracy: 0.9916 4224/6993 [=================>............] - ETA: 0s - loss: 0.0892 - accuracy: 0.9917 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1349 - accuracy: 0.9894 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1304 - accuracy: 0.9896 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1171 - accuracy: 0.9892 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1142 - accuracy: 0.9893 - val_loss: 1.4278 - val_accuracy: 0.9363 Epoch 465/500 128/6993 [..............................] - ETA: 0s - loss: 0.0977 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.0402 - accuracy: 0.9877 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0651 - accuracy: 0.9910 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0856 - accuracy: 0.9913 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0793 - accuracy: 0.9918 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0732 - accuracy: 0.9919 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0907 - accuracy: 0.9913 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0876 - accuracy: 0.9914 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0918 - accuracy: 0.9908 6784/6993 [============================>.] - ETA: 0s - loss: 0.0907 - accuracy: 0.9907 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0881 - accuracy: 0.9910 - val_loss: 1.5577 - val_accuracy: 0.9312 Epoch 466/500 128/6993 [..............................] - ETA: 0s - loss: 0.0177 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0485 - accuracy: 0.9933 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0726 - accuracy: 0.9928 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0625 - accuracy: 0.9909 3200/6993 [============>.................] - ETA: 0s - loss: 0.0616 - accuracy: 0.9906 4096/6993 [================>.............] - ETA: 0s - loss: 0.0652 - accuracy: 0.9915 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0577 - accuracy: 0.9918 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0635 - accuracy: 0.9917 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0599 - accuracy: 0.9920 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0568 - accuracy: 0.9923 - val_loss: 2.0684 - val_accuracy: 0.9338 Epoch 467/500 128/6993 [..............................] - ETA: 0s - loss: 0.1005 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0275 - accuracy: 0.9922 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1289 - accuracy: 0.9941 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1064 - accuracy: 0.9944 3200/6993 [============>.................] - ETA: 0s - loss: 0.0817 - accuracy: 0.9944 4096/6993 [================>.............] - ETA: 0s - loss: 0.0849 - accuracy: 0.9934 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1038 - accuracy: 0.9930 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1050 - accuracy: 0.9913 6656/6993 [===========================>..] - ETA: 0s - loss: 0.2162 - accuracy: 0.9905 6993/6993 [==============================] - 1s 83us/sample - loss: 0.2106 - accuracy: 0.9906 - val_loss: 1.9018 - val_accuracy: 0.9262 Epoch 468/500 128/6993 [..............................] - ETA: 0s - loss: 0.0067 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.1499 - accuracy: 0.9935 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0817 - accuracy: 0.9941 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0639 - accuracy: 0.9938 3200/6993 [============>.................] - ETA: 0s - loss: 0.0659 - accuracy: 0.9928 4096/6993 [================>.............] - ETA: 0s - loss: 0.0773 - accuracy: 0.9924 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0709 - accuracy: 0.9928 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1023 - accuracy: 0.9925 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1232 - accuracy: 0.9914 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1179 - accuracy: 0.9914 - val_loss: 1.5693 - val_accuracy: 0.9328 Epoch 469/500 128/6993 [..............................] - ETA: 0s - loss: 0.0163 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0481 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0412 - accuracy: 0.9927 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0545 - accuracy: 0.9900 3456/6993 [=============>................] - ETA: 0s - loss: 0.0456 - accuracy: 0.9916 4352/6993 [=================>............] - ETA: 0s - loss: 0.0605 - accuracy: 0.9908 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0633 - accuracy: 0.9908 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0595 - accuracy: 0.9909 6912/6993 [============================>.] - ETA: 0s - loss: 0.0663 - accuracy: 0.9900 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0658 - accuracy: 0.9901 - val_loss: 1.7847 - val_accuracy: 0.9272 Epoch 470/500 128/6993 [..............................] - ETA: 0s - loss: 0.0182 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1579 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1675 - accuracy: 0.9894 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1342 - accuracy: 0.9910 3456/6993 [=============>................] - ETA: 0s - loss: 0.1457 - accuracy: 0.9887 4224/6993 [=================>............] - ETA: 0s - loss: 0.1711 - accuracy: 0.9879 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1596 - accuracy: 0.9877 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1592 - accuracy: 0.9876 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1488 - accuracy: 0.9878 6993/6993 [==============================] - 1s 79us/sample - loss: 0.1421 - accuracy: 0.9881 - val_loss: 1.4533 - val_accuracy: 0.9343 Epoch 471/500 128/6993 [..............................] - ETA: 0s - loss: 0.0150 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0602 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0412 - accuracy: 0.9911 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1687 - accuracy: 0.9870 3456/6993 [=============>................] - ETA: 0s - loss: 0.1588 - accuracy: 0.9881 4352/6993 [=================>............] - ETA: 0s - loss: 0.1481 - accuracy: 0.9878 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1275 - accuracy: 0.9889 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1155 - accuracy: 0.9890 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1148 - accuracy: 0.9893 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1107 - accuracy: 0.9896 - val_loss: 1.5749 - val_accuracy: 0.9338 Epoch 472/500 128/6993 [..............................] - ETA: 0s - loss: 0.0256 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1668 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0891 - accuracy: 0.9922 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0873 - accuracy: 0.9918 3328/6993 [=============>................] - ETA: 0s - loss: 0.0856 - accuracy: 0.9922 3968/6993 [================>.............] - ETA: 0s - loss: 0.1779 - accuracy: 0.9912 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1939 - accuracy: 0.9911 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1933 - accuracy: 0.9904 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1826 - accuracy: 0.9901 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1773 - accuracy: 0.9900 6993/6993 [==============================] - 1s 94us/sample - loss: 0.1674 - accuracy: 0.9897 - val_loss: 1.4087 - val_accuracy: 0.9317 Epoch 473/500 128/6993 [..............................] - ETA: 0s - loss: 0.0042 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0506 - accuracy: 0.9951 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0437 - accuracy: 0.9928 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0524 - accuracy: 0.9910 3456/6993 [=============>................] - ETA: 0s - loss: 0.0892 - accuracy: 0.9890 4096/6993 [================>.............] - ETA: 0s - loss: 0.0904 - accuracy: 0.9890 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0842 - accuracy: 0.9893 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1475 - accuracy: 0.9885 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1378 - accuracy: 0.9888 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1363 - accuracy: 0.9890 - val_loss: 1.3752 - val_accuracy: 0.9388 Epoch 474/500 128/6993 [..............................] - ETA: 0s - loss: 0.0092 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0608 - accuracy: 0.9912 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1496 - accuracy: 0.9865 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1334 - accuracy: 0.9881 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1057 - accuracy: 0.9891 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1294 - accuracy: 0.9888 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1131 - accuracy: 0.9897 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0989 - accuracy: 0.9906 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1004 - accuracy: 0.9907 - val_loss: 1.3892 - val_accuracy: 0.9328 Epoch 475/500 128/6993 [..............................] - ETA: 0s - loss: 0.0088 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0595 - accuracy: 0.9971 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0391 - accuracy: 0.9964 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0481 - accuracy: 0.9943 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1263 - accuracy: 0.9919 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1195 - accuracy: 0.9920 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1060 - accuracy: 0.9918 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1066 - accuracy: 0.9919 6912/6993 [============================>.] - ETA: 0s - loss: 0.1068 - accuracy: 0.9918 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1056 - accuracy: 0.9918 - val_loss: 1.5230 - val_accuracy: 0.9323 Epoch 476/500 128/6993 [..............................] - ETA: 0s - loss: 0.3183 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0913 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0573 - accuracy: 0.9916 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1013 - accuracy: 0.9900 3072/6993 [============>.................] - ETA: 0s - loss: 0.1001 - accuracy: 0.9906 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0866 - accuracy: 0.9904 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0804 - accuracy: 0.9909 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0844 - accuracy: 0.9903 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0868 - accuracy: 0.9899 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0834 - accuracy: 0.9901 - val_loss: 1.4390 - val_accuracy: 0.9297 Epoch 477/500 128/6993 [..............................] - ETA: 0s - loss: 0.1585 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1049 - accuracy: 0.9799 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1317 - accuracy: 0.9832 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0964 - accuracy: 0.9864 3328/6993 [=============>................] - ETA: 0s - loss: 0.0767 - accuracy: 0.9886 4224/6993 [=================>............] - ETA: 0s - loss: 0.0795 - accuracy: 0.9891 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0911 - accuracy: 0.9877 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0829 - accuracy: 0.9883 6784/6993 [============================>.] - ETA: 0s - loss: 0.0805 - accuracy: 0.9892 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0797 - accuracy: 0.9894 - val_loss: 1.5264 - val_accuracy: 0.9338 Epoch 478/500 128/6993 [..............................] - ETA: 0s - loss: 0.3151 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.2634 - accuracy: 0.9877 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1767 - accuracy: 0.9902 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1670 - accuracy: 0.9896 3200/6993 [============>.................] - ETA: 0s - loss: 0.1232 - accuracy: 0.9916 3968/6993 [================>.............] - ETA: 0s - loss: 0.1057 - accuracy: 0.9912 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1008 - accuracy: 0.9901 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0952 - accuracy: 0.9906 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0884 - accuracy: 0.9912 6784/6993 [============================>.] - ETA: 0s - loss: 0.0854 - accuracy: 0.9912 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0861 - accuracy: 0.9910 - val_loss: 1.5572 - val_accuracy: 0.9312 Epoch 479/500 128/6993 [..............................] - ETA: 0s - loss: 0.0086 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0561 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1093 - accuracy: 0.9933 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1102 - accuracy: 0.9907 3456/6993 [=============>................] - ETA: 0s - loss: 0.1039 - accuracy: 0.9896 4352/6993 [=================>............] - ETA: 0s - loss: 0.0943 - accuracy: 0.9890 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0930 - accuracy: 0.9890 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1155 - accuracy: 0.9888 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1076 - accuracy: 0.9890 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1016 - accuracy: 0.9890 - val_loss: 1.6269 - val_accuracy: 0.9323 Epoch 480/500 128/6993 [..............................] - ETA: 0s - loss: 0.0137 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.3465 - accuracy: 0.9877 1536/6993 [=====>........................] - ETA: 0s - loss: 0.2749 - accuracy: 0.9876 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1906 - accuracy: 0.9905 2944/6993 [===========>..................] - ETA: 0s - loss: 0.2013 - accuracy: 0.9895 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1855 - accuracy: 0.9892 4352/6993 [=================>............] - ETA: 0s - loss: 0.1657 - accuracy: 0.9899 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1488 - accuracy: 0.9904 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1381 - accuracy: 0.9909 6912/6993 [============================>.] - ETA: 0s - loss: 0.1313 - accuracy: 0.9910 6993/6993 [==============================] - 1s 87us/sample - loss: 0.1298 - accuracy: 0.9911 - val_loss: 1.8564 - val_accuracy: 0.9343 Epoch 481/500 128/6993 [..............................] - ETA: 0s - loss: 0.1619 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0570 - accuracy: 0.9951 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1789 - accuracy: 0.9922 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1529 - accuracy: 0.9914 3328/6993 [=============>................] - ETA: 0s - loss: 0.1634 - accuracy: 0.9913 3968/6993 [================>.............] - ETA: 0s - loss: 0.1595 - accuracy: 0.9909 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1579 - accuracy: 0.9913 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1439 - accuracy: 0.9916 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1325 - accuracy: 0.9917 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1214 - accuracy: 0.9920 6993/6993 [==============================] - 1s 94us/sample - loss: 0.1168 - accuracy: 0.9918 - val_loss: 1.7446 - val_accuracy: 0.9307 Epoch 482/500 128/6993 [..............................] - ETA: 0s - loss: 0.0037 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.1011 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0685 - accuracy: 0.9898 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0792 - accuracy: 0.9895 3328/6993 [=============>................] - ETA: 0s - loss: 0.0993 - accuracy: 0.9874 4224/6993 [=================>............] - ETA: 0s - loss: 0.0906 - accuracy: 0.9886 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1000 - accuracy: 0.9889 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0997 - accuracy: 0.9886 6784/6993 [============================>.] - ETA: 0s - loss: 0.1008 - accuracy: 0.9889 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1003 - accuracy: 0.9888 - val_loss: 1.5796 - val_accuracy: 0.9358 Epoch 483/500 128/6993 [..............................] - ETA: 0s - loss: 8.2884e-04 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0313 - accuracy: 0.9932 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1755 - accuracy: 0.9911 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1430 - accuracy: 0.9907 3328/6993 [=============>................] - ETA: 0s - loss: 0.1687 - accuracy: 0.9910 4224/6993 [=================>............] - ETA: 0s - loss: 0.1713 - accuracy: 0.9912 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1487 - accuracy: 0.9908 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1375 - accuracy: 0.9910 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1239 - accuracy: 0.9914 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1376 - accuracy: 0.9913 - val_loss: 1.7761 - val_accuracy: 0.9348 Epoch 484/500 128/6993 [..............................] - ETA: 0s - loss: 0.0050 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0110 - accuracy: 0.9967 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0338 - accuracy: 0.9952 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0608 - accuracy: 0.9937 3456/6993 [=============>................] - ETA: 0s - loss: 0.0752 - accuracy: 0.9925 4224/6993 [=================>............] - ETA: 0s - loss: 0.0704 - accuracy: 0.9934 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0847 - accuracy: 0.9924 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1031 - accuracy: 0.9915 6784/6993 [============================>.] - ETA: 0s - loss: 0.0958 - accuracy: 0.9919 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0937 - accuracy: 0.9918 - val_loss: 1.6591 - val_accuracy: 0.9343 Epoch 485/500 128/6993 [..............................] - ETA: 0s - loss: 0.0349 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0144 - accuracy: 0.9955 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0242 - accuracy: 0.9946 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0309 - accuracy: 0.9942 3072/6993 [============>.................] - ETA: 0s - loss: 0.0349 - accuracy: 0.9948 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0827 - accuracy: 0.9940 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0966 - accuracy: 0.9933 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0883 - accuracy: 0.9935 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0834 - accuracy: 0.9935 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0863 - accuracy: 0.9926 - val_loss: 1.8135 - val_accuracy: 0.9307 Epoch 486/500 128/6993 [..............................] - ETA: 0s - loss: 0.0100 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.2901 - accuracy: 0.9831 1536/6993 [=====>........................] - ETA: 0s - loss: 0.2307 - accuracy: 0.9831 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1624 - accuracy: 0.9861 3200/6993 [============>.................] - ETA: 0s - loss: 0.1317 - accuracy: 0.9881 4096/6993 [================>.............] - ETA: 0s - loss: 0.1141 - accuracy: 0.9895 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1887 - accuracy: 0.9894 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1898 - accuracy: 0.9891 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1758 - accuracy: 0.9894 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1650 - accuracy: 0.9898 - val_loss: 1.7482 - val_accuracy: 0.9262 Epoch 487/500 128/6993 [..............................] - ETA: 0s - loss: 0.0779 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1445 - accuracy: 0.9877 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1089 - accuracy: 0.9886 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0946 - accuracy: 0.9891 3328/6993 [=============>................] - ETA: 0s - loss: 0.1084 - accuracy: 0.9889 4096/6993 [================>.............] - ETA: 0s - loss: 0.1017 - accuracy: 0.9893 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0971 - accuracy: 0.9898 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0898 - accuracy: 0.9895 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0821 - accuracy: 0.9905 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0772 - accuracy: 0.9905 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0714 - accuracy: 0.9908 - val_loss: 1.6995 - val_accuracy: 0.9312 Epoch 488/500 128/6993 [..............................] - ETA: 0s - loss: 0.0205 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0549 - accuracy: 0.9922 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0583 - accuracy: 0.9898 1664/6993 [======>.......................] - ETA: 0s - loss: 0.2031 - accuracy: 0.9850 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1940 - accuracy: 0.9854 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1863 - accuracy: 0.9855 3072/6993 [============>.................] - ETA: 0s - loss: 0.1580 - accuracy: 0.9870 3456/6993 [=============>................] - ETA: 0s - loss: 0.1694 - accuracy: 0.9870 3968/6993 [================>.............] - ETA: 0s - loss: 0.1654 - accuracy: 0.9879 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1702 - accuracy: 0.9872 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1603 - accuracy: 0.9878 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1697 - accuracy: 0.9879 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1797 - accuracy: 0.9880 6993/6993 [==============================] - 1s 186us/sample - loss: 0.1765 - accuracy: 0.9877 - val_loss: 1.6674 - val_accuracy: 0.9333 Epoch 489/500 128/6993 [..............................] - ETA: 1s - loss: 0.7526 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 1s - loss: 0.1708 - accuracy: 0.9937 1024/6993 [===>..........................] - ETA: 1s - loss: 0.1735 - accuracy: 0.9873 1536/6993 [=====>........................] - ETA: 0s - loss: 0.3139 - accuracy: 0.9896 1792/6993 [======>.......................] - ETA: 0s - loss: 0.2740 - accuracy: 0.9894 2048/6993 [=======>......................] - ETA: 0s - loss: 0.2545 - accuracy: 0.9878 2560/6993 [=========>....................] - ETA: 0s - loss: 0.2211 - accuracy: 0.9871 2944/6993 [===========>..................] - ETA: 0s - loss: 0.2096 - accuracy: 0.9871 3456/6993 [=============>................] - ETA: 0s - loss: 0.1797 - accuracy: 0.9887 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1661 - accuracy: 0.9885 4352/6993 [=================>............] - ETA: 0s - loss: 0.1577 - accuracy: 0.9883 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1512 - accuracy: 0.9887 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1440 - accuracy: 0.9891 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1343 - accuracy: 0.9892 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1288 - accuracy: 0.9893 6784/6993 [============================>.] - ETA: 0s - loss: 0.1225 - accuracy: 0.9895 6993/6993 [==============================] - 1s 156us/sample - loss: 0.1192 - accuracy: 0.9897 - val_loss: 1.4152 - val_accuracy: 0.9338 Epoch 490/500 128/6993 [..............................] - ETA: 0s - loss: 0.0040 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0470 - accuracy: 0.9935 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0325 - accuracy: 0.9953 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1336 - accuracy: 0.9941 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1225 - accuracy: 0.9922 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1281 - accuracy: 0.9922 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1087 - accuracy: 0.9924 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1128 - accuracy: 0.9916 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1285 - accuracy: 0.9910 6912/6993 [============================>.] - ETA: 0s - loss: 0.1167 - accuracy: 0.9912 6993/6993 [==============================] - 1s 89us/sample - loss: 0.1172 - accuracy: 0.9911 - val_loss: 1.3019 - val_accuracy: 0.9368 Epoch 491/500 128/6993 [..............................] - ETA: 0s - loss: 0.3272 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.5318 - accuracy: 0.9883 1280/6993 [====>.........................] - ETA: 0s - loss: 0.3296 - accuracy: 0.9883 2048/6993 [=======>......................] - ETA: 0s - loss: 0.2377 - accuracy: 0.9888 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1849 - accuracy: 0.9890 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1441 - accuracy: 0.9898 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1251 - accuracy: 0.9900 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1230 - accuracy: 0.9904 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1171 - accuracy: 0.9900 6784/6993 [============================>.] - ETA: 0s - loss: 0.1113 - accuracy: 0.9903 6993/6993 [==============================] - 1s 94us/sample - loss: 0.1137 - accuracy: 0.9901 - val_loss: 1.5658 - val_accuracy: 0.9312 Epoch 492/500 128/6993 [..............................] - ETA: 0s - loss: 0.0099 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0578 - accuracy: 0.9922 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1248 - accuracy: 0.9896 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1596 - accuracy: 0.9913 2944/6993 [===========>..................] - ETA: 0s - loss: 0.2042 - accuracy: 0.9901 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1902 - accuracy: 0.9887 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1602 - accuracy: 0.9897 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1605 - accuracy: 0.9898 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1562 - accuracy: 0.9895 6993/6993 [==============================] - 1s 87us/sample - loss: 0.1589 - accuracy: 0.9898 - val_loss: 1.5829 - val_accuracy: 0.9312 Epoch 493/500 128/6993 [..............................] - ETA: 0s - loss: 0.0169 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0612 - accuracy: 0.9932 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0499 - accuracy: 0.9922 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0424 - accuracy: 0.9937 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0607 - accuracy: 0.9930 4352/6993 [=================>............] - ETA: 0s - loss: 0.0603 - accuracy: 0.9926 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0795 - accuracy: 0.9910 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0717 - accuracy: 0.9917 6912/6993 [============================>.] - ETA: 0s - loss: 0.0886 - accuracy: 0.9912 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0876 - accuracy: 0.9913 - val_loss: 1.5639 - val_accuracy: 0.9363 Epoch 494/500 128/6993 [..............................] - ETA: 0s - loss: 0.0095 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0606 - accuracy: 0.9911 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0480 - accuracy: 0.9922 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0812 - accuracy: 0.9926 3456/6993 [=============>................] - ETA: 0s - loss: 0.0755 - accuracy: 0.9931 4224/6993 [=================>............] - ETA: 0s - loss: 0.1195 - accuracy: 0.9934 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1233 - accuracy: 0.9924 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1215 - accuracy: 0.9917 6784/6993 [============================>.] - ETA: 0s - loss: 0.1132 - accuracy: 0.9912 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1109 - accuracy: 0.9913 - val_loss: 1.6511 - val_accuracy: 0.9358 Epoch 495/500 128/6993 [..............................] - ETA: 0s - loss: 0.1477 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0913 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0556 - accuracy: 0.9933 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0852 - accuracy: 0.9922 3456/6993 [=============>................] - ETA: 0s - loss: 0.0792 - accuracy: 0.9913 4224/6993 [=================>............] - ETA: 0s - loss: 0.0804 - accuracy: 0.9910 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0728 - accuracy: 0.9912 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0775 - accuracy: 0.9908 6784/6993 [============================>.] - ETA: 0s - loss: 0.0774 - accuracy: 0.9898 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0759 - accuracy: 0.9898 - val_loss: 1.5181 - val_accuracy: 0.9348 Epoch 496/500 128/6993 [..............................] - ETA: 0s - loss: 0.2450 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0996 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0582 - accuracy: 0.9904 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0452 - accuracy: 0.9922 3456/6993 [=============>................] - ETA: 0s - loss: 0.1778 - accuracy: 0.9922 4224/6993 [=================>............] - ETA: 0s - loss: 0.1763 - accuracy: 0.9910 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1615 - accuracy: 0.9914 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1888 - accuracy: 0.9905 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1723 - accuracy: 0.9905 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1655 - accuracy: 0.9903 - val_loss: 1.5961 - val_accuracy: 0.9373 Epoch 497/500 128/6993 [..............................] - ETA: 0s - loss: 0.1966 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1748 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1309 - accuracy: 0.9905 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1134 - accuracy: 0.9918 3456/6993 [=============>................] - ETA: 0s - loss: 0.1061 - accuracy: 0.9910 4224/6993 [=================>............] - ETA: 0s - loss: 0.0903 - accuracy: 0.9912 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0765 - accuracy: 0.9924 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0904 - accuracy: 0.9922 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0946 - accuracy: 0.9922 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0899 - accuracy: 0.9924 - val_loss: 1.9794 - val_accuracy: 0.9338 Epoch 498/500 128/6993 [..............................] - ETA: 0s - loss: 0.1438 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.1621 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1272 - accuracy: 0.9901 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1107 - accuracy: 0.9902 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1334 - accuracy: 0.9888 3328/6993 [=============>................] - ETA: 0s - loss: 0.1285 - accuracy: 0.9877 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1381 - accuracy: 0.9875 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1369 - accuracy: 0.9864 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1495 - accuracy: 0.9857 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1453 - accuracy: 0.9859 6784/6993 [============================>.] - ETA: 0s - loss: 0.1517 - accuracy: 0.9863 6993/6993 [==============================] - 1s 101us/sample - loss: 0.1558 - accuracy: 0.9863 - val_loss: 1.6687 - val_accuracy: 0.9312 Epoch 499/500 128/6993 [..............................] - ETA: 0s - loss: 0.0780 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0982 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0899 - accuracy: 0.9879 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0695 - accuracy: 0.9908 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0681 - accuracy: 0.9908 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0785 - accuracy: 0.9897 4224/6993 [=================>............] - ETA: 0s - loss: 0.0699 - accuracy: 0.9898 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0661 - accuracy: 0.9905 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0707 - accuracy: 0.9904 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0776 - accuracy: 0.9904 6912/6993 [============================>.] - ETA: 0s - loss: 0.0743 - accuracy: 0.9905 6993/6993 [==============================] - 1s 103us/sample - loss: 0.0734 - accuracy: 0.9906 - val_loss: 1.7046 - val_accuracy: 0.9383 Epoch 500/500 128/6993 [..............................] - ETA: 0s - loss: 0.0042 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0239 - accuracy: 0.9911 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0676 - accuracy: 0.9902 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0517 - accuracy: 0.9922 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0570 - accuracy: 0.9929 3456/6993 [=============>................] - ETA: 0s - loss: 0.0538 - accuracy: 0.9931 4096/6993 [================>.............] - ETA: 0s - loss: 0.0511 - accuracy: 0.9927 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0611 - accuracy: 0.9920 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0548 - accuracy: 0.9926 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0548 - accuracy: 0.9932 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0562 - accuracy: 0.9932 6912/6993 [============================>.] - ETA: 0s - loss: 0.0551 - accuracy: 0.9929 6993/6993 [==============================] - 1s 116us/sample - loss: 0.0549 - accuracy: 0.9927 - val_loss: 1.8360 - val_accuracy: 0.9373 1019/1019 - 0s - loss: 1.4494 - accuracy: 0.9352 Test accuracy: 0.9352306
And I set the epochs as 500 and use rmsprop optimizer, and finally get more than 93% accuracy for this model.
def plot_history(train_losses, train_accs, val_losses, val_accs, model_name="", return_fig=True):
fig, axs = plt.subplots(2, figsize=(15, 10))
axs[0].plot(train_accs, label="train accuracy")
axs[0].plot(val_accs, label="valid accuracy")
axs[0].set_ylabel("Accuracy")
axs[0].legend(loc="lower right")
axs[0].set_title("Accuracy eval for " + model_name)
axs[1].plot(train_losses, label="train error")
axs[1].plot(val_losses, label="valid error")
axs[1].set_ylabel("Error")
axs[1].set_xlabel("Epoch")
axs[1].legend(loc="upper right")
axs[1].set_title("Error eval for " + model_name)
fig.tight_layout()
import json
%matplotlib inline
cnn1_val_log = "logs/cnn1/CNN1_060422_122834.json"
fcnn1_val_log = "logs/fcnn1/FCNN1_060422_124733.json"
fcnn2_val_log = "logs/fcnn2/FCNN2_060422_125313.json"
with open(cnn1_val_log, 'r') as cnn1:
cnn1_val_json = json.load(cnn1)
with open(fcnn1_val_log, 'r') as fcnn1:
fcnn1_val_json = json.load(fcnn1)
with open(fcnn2_val_log, 'r') as fcnn2:
fcnn2_val_json = json.load(fcnn2)
plot_history(cnn1_val_json["train_losses"],
cnn1_val_json["train_accs"],
cnn1_val_json["val_losses"],
cnn1_val_json["val_accs"],
model_name="CNN1")
plot_history(fcnn1_val_json["train_losses"],
fcnn1_val_json["train_accs"],
fcnn1_val_json["val_losses"],
fcnn1_val_json["val_accs"],
model_name="FCNN1")
plot_history(fcnn2_val_json["train_losses"],
fcnn2_val_json["train_accs"],
fcnn2_val_json["val_losses"],
fcnn2_val_json["val_accs"],
model_name="FCNN2")
You can run the "python eval.py logs/cnn1/CNN1_060422_122834.json 5" in the terminal of Pycharm.(Warning: the right Virtual environment should be venv_python3.6) And you will get result as below shown.
Or you can directly run ! python eval.py logs/cnn1/CNN1_060422_122834.json 5 in the jupyter notebook
! python eval.py logs/cnn1/CNN1_060422_122834.json 5
Training model for iteration 0... Train on 3595 samples, validate on 899 samples Epoch 1/28 32/3595 [..............................] - ETA: 4:01 - loss: 3.1739 - accuracy: 0.0938 160/3595 [>.............................] - ETA: 47s - loss: 3.0022 - accuracy: 0.0875 288/3595 [=>............................] - ETA: 26s - loss: 2.9958 - accuracy: 0.1076 416/3595 [==>...........................] - ETA: 18s - loss: 2.9446 - accuracy: 0.1130 544/3595 [===>..........................] - ETA: 13s - loss: 2.9213 - accuracy: 0.1250 704/3595 [====>.........................] - ETA: 10s - loss: 2.8650 - accuracy: 0.1335 832/3595 [=====>........................] - ETA: 8s - loss: 2.8421 - accuracy: 0.1358 960/3595 [=======>......................] - ETA: 7s - loss: 2.8064 - accuracy: 0.1406 1120/3595 [========>.....................] - ETA: 5s - loss: 2.7765 - accuracy: 0.1446 1248/3595 [=========>....................] - ETA: 5s - loss: 2.7520 - accuracy: 0.1498 1408/3595 [==========>...................] - ETA: 4s - loss: 2.7320 - accuracy: 0.1527 1536/3595 [===========>..................] - ETA: 3s - loss: 2.7275 - accuracy: 0.1536 1696/3595 [=============>................] - ETA: 3s - loss: 2.6989 - accuracy: 0.1592 1824/3595 [==============>...............] - ETA: 2s - loss: 2.6530 - accuracy: 0.1678 1952/3595 [===============>..............] - ETA: 2s - loss: 2.6372 - accuracy: 0.1711 2048/3595 [================>.............] - ETA: 2s - loss: 2.6195 - accuracy: 0.1743 2176/3595 [=================>............] - ETA: 2s - loss: 2.5962 - accuracy: 0.1801 2304/3595 [==================>...........] - ETA: 1s - loss: 2.5731 - accuracy: 0.1832 2432/3595 [===================>..........] - ETA: 1s - loss: 2.5584 - accuracy: 0.1834 2560/3595 [====================>.........] - ETA: 1s - loss: 2.5358 - accuracy: 0.1895 2720/3595 [=====================>........] - ETA: 1s - loss: 2.5231 - accuracy: 0.1941 2848/3595 [======================>.......] - ETA: 0s - loss: 2.5070 - accuracy: 0.1998 2976/3595 [=======================>......] - ETA: 0s - loss: 2.4885 - accuracy: 0.2036 3104/3595 [========================>.....] - ETA: 0s - loss: 2.4683 - accuracy: 0.2101 3232/3595 [=========================>....] - ETA: 0s - loss: 2.4579 - accuracy: 0.2113 3360/3595 [===========================>..] - ETA: 0s - loss: 2.4462 - accuracy: 0.2152 3488/3595 [============================>.] - ETA: 0s - loss: 2.4300 - accuracy: 0.2185 3595/3595 [==============================] - 4s 1ms/sample - loss: 2.4199 - accuracy: 0.2225 - val_loss: 2.0674 - val_accuracy: 0.2636 Epoch 2/28 32/3595 [..............................] - ETA: 1s - loss: 1.9431 - accuracy: 0.2500 160/3595 [>.............................] - ETA: 1s - loss: 1.9284 - accuracy: 0.3125 288/3595 [=>............................] - ETA: 1s - loss: 2.0091 - accuracy: 0.3125 416/3595 [==>...........................] - ETA: 1s - loss: 1.9981 - accuracy: 0.3077 544/3595 [===>..........................] - ETA: 1s - loss: 1.9940 - accuracy: 0.3143 672/3595 [====>.........................] - ETA: 1s - loss: 1.9524 - accuracy: 0.3333 800/3595 [=====>........................] - ETA: 1s - loss: 1.9238 - accuracy: 0.3425 928/3595 [======>.......................] - ETA: 1s - loss: 1.9094 - accuracy: 0.3427 1056/3595 [=======>......................] - ETA: 1s - loss: 1.9182 - accuracy: 0.3419 1184/3595 [========>.....................] - ETA: 1s - loss: 1.9344 - accuracy: 0.3463 1312/3595 [=========>....................] - ETA: 1s - loss: 1.9421 - accuracy: 0.3415 1472/3595 [===========>..................] - ETA: 1s - loss: 1.9379 - accuracy: 0.3431 1600/3595 [============>.................] - ETA: 0s - loss: 1.9384 - accuracy: 0.3419 1728/3595 [=============>................] - ETA: 0s - loss: 1.9578 - accuracy: 0.3374 1856/3595 [==============>...............] - ETA: 0s - loss: 1.9562 - accuracy: 0.3367 1984/3595 [===============>..............] - ETA: 0s - loss: 1.9371 - accuracy: 0.3407
2022-04-11 22:22:57.101545: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll 2022-04-11 22:23:16.420593: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 2022-04-11 22:23:16.425999: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll 2022-04-11 22:23:16.532635: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 22:23:16.532665: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 22:23:16.538517: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 22:23:17.264519: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 22:23:17.264556: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 22:23:17.264563: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 22:23:17.273977: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) WARNING:tensorflow:From D:\Programs\Anaconda_app\envs\comp47650_env\lib\site-packages\tensorflow_core\python\ops\resource_variable_ops.py:1630: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version. Instructions for updating: If using Keras pass *_constraint arguments to layers. 2022-04-11 22:23:17.400686: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 22:23:17.400711: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 22:23:17.406780: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 22:23:19.053556: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll 2022-04-11 22:23:19.555876: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll 2022-04-11 22:23:20.487343: W tensorflow/stream_executor/cuda/redzone_allocator.cc:312] Internal: Invoking ptxas not supported on Windows Relying on driver to perform ptx compilation. This message will be only logged once. 2022-04-11 22:24:13.328498: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 22:24:13.328523: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 22:24:13.334518: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 22:24:13.334591: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 22:24:13.334601: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 22:24:13.334607: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 22:24:13.340609: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) 2022-04-11 22:24:14.620209: W tensorflow/python/util/util.cc:299] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them. 2022-04-11 22:24:16.606577: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 22:24:16.606618: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 22:24:16.611547: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 22:24:16.611638: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 22:24:16.611646: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 22:24:16.611669: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 22:24:16.617809: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) 2022-04-11 22:25:18.106373: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
2112/3595 [================>.............] - ETA: 0s - loss: 1.9351 - accuracy: 0.3419 2240/3595 [=================>............] - ETA: 0s - loss: 1.9318 - accuracy: 0.3424 2368/3595 [==================>...........] - ETA: 0s - loss: 1.9208 - accuracy: 0.3463 2496/3595 [===================>..........] - ETA: 0s - loss: 1.9164 - accuracy: 0.3450 2624/3595 [====================>.........] - ETA: 0s - loss: 1.9234 - accuracy: 0.3430 2752/3595 [=====================>........] - ETA: 0s - loss: 1.9279 - accuracy: 0.3416 2880/3595 [=======================>......] - ETA: 0s - loss: 1.9196 - accuracy: 0.3444 3008/3595 [========================>.....] - ETA: 0s - loss: 1.9111 - accuracy: 0.3457 3104/3595 [========================>.....] - ETA: 0s - loss: 1.9068 - accuracy: 0.3476 3200/3595 [=========================>....] - ETA: 0s - loss: 1.8969 - accuracy: 0.3497 3328/3595 [==========================>...] - ETA: 0s - loss: 1.8893 - accuracy: 0.3516 3456/3595 [===========================>..] - ETA: 0s - loss: 1.8873 - accuracy: 0.3530 3584/3595 [============================>.] - ETA: 0s - loss: 1.8824 - accuracy: 0.3513 3595/3595 [==============================] - 2s 537us/sample - loss: 1.8815 - accuracy: 0.3510 - val_loss: 1.6561 - val_accuracy: 0.4116 Epoch 3/28 32/3595 [..............................] - ETA: 0s - loss: 1.8631 - accuracy: 0.4062 160/3595 [>.............................] - ETA: 1s - loss: 1.6387 - accuracy: 0.4437 320/3595 [=>............................] - ETA: 1s - loss: 1.6039 - accuracy: 0.4469 480/3595 [===>..........................] - ETA: 1s - loss: 1.6814 - accuracy: 0.4229 608/3595 [====>.........................] - ETA: 1s - loss: 1.6932 - accuracy: 0.4095 768/3595 [=====>........................] - ETA: 1s - loss: 1.6971 - accuracy: 0.4036 928/3595 [======>.......................] - ETA: 1s - loss: 1.7053 - accuracy: 0.3987 1088/3595 [========>.....................] - ETA: 1s - loss: 1.7103 - accuracy: 0.4017 1248/3595 [=========>....................] - ETA: 0s - loss: 1.7036 - accuracy: 0.4006 1376/3595 [==========>...................] - ETA: 0s - loss: 1.7037 - accuracy: 0.3983 1536/3595 [===========>..................] - ETA: 0s - loss: 1.7052 - accuracy: 0.3984 1696/3595 [=============>................] - ETA: 0s - loss: 1.6928 - accuracy: 0.4045 1824/3595 [==============>...............] - ETA: 0s - loss: 1.6805 - accuracy: 0.4079 1984/3595 [===============>..............] - ETA: 0s - loss: 1.6848 - accuracy: 0.4052 2144/3595 [================>.............] - ETA: 0s - loss: 1.6778 - accuracy: 0.4095 2304/3595 [==================>...........] - ETA: 0s - loss: 1.6723 - accuracy: 0.4115 2432/3595 [===================>..........] - ETA: 0s - loss: 1.6789 - accuracy: 0.4104 2592/3595 [====================>.........] - ETA: 0s - loss: 1.6662 - accuracy: 0.4159 2752/3595 [=====================>........] - ETA: 0s - loss: 1.6660 - accuracy: 0.4150 2912/3595 [=======================>......] - ETA: 0s - loss: 1.6664 - accuracy: 0.4155 3040/3595 [========================>.....] - ETA: 0s - loss: 1.6582 - accuracy: 0.4168 3200/3595 [=========================>....] - ETA: 0s - loss: 1.6549 - accuracy: 0.4178 3360/3595 [===========================>..] - ETA: 0s - loss: 1.6532 - accuracy: 0.4179 3488/3595 [============================>.] - ETA: 0s - loss: 1.6550 - accuracy: 0.4166 3595/3595 [==============================] - 2s 439us/sample - loss: 1.6596 - accuracy: 0.4147 - val_loss: 1.4787 - val_accuracy: 0.4538 Epoch 4/28 32/3595 [..............................] - ETA: 1s - loss: 1.5809 - accuracy: 0.4688 192/3595 [>.............................] - ETA: 1s - loss: 1.6548 - accuracy: 0.4115 320/3595 [=>............................] - ETA: 1s - loss: 1.6122 - accuracy: 0.4250 480/3595 [===>..........................] - ETA: 1s - loss: 1.5826 - accuracy: 0.4354 608/3595 [====>.........................] - ETA: 1s - loss: 1.5757 - accuracy: 0.4424 736/3595 [=====>........................] - ETA: 1s - loss: 1.5770 - accuracy: 0.4375 896/3595 [======>.......................] - ETA: 1s - loss: 1.5954 - accuracy: 0.4252 1024/3595 [=======>......................] - ETA: 1s - loss: 1.5680 - accuracy: 0.4336 1184/3595 [========>.....................] - ETA: 1s - loss: 1.5761 - accuracy: 0.4333 1312/3595 [=========>....................] - ETA: 1s - loss: 1.5844 - accuracy: 0.4268 1472/3595 [===========>..................] - ETA: 0s - loss: 1.5687 - accuracy: 0.4314 1600/3595 [============>.................] - ETA: 0s - loss: 1.5606 - accuracy: 0.4387
name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 22:25:18.106398: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 22:25:18.112220: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 22:25:18.112291: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 22:25:18.112301: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 22:25:18.112307: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 22:25:18.118144: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) 2022-04-11 22:26:19.888521: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 22:26:19.888547: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 22:26:19.894417: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 22:26:19.894489: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 22:26:19.894499: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 22:26:19.894504: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 22:26:19.900507: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) 2022-04-11 22:27:23.768799: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0
1760/3595 [=============>................] - ETA: 0s - loss: 1.5710 - accuracy: 0.4347 1888/3595 [==============>...............] - ETA: 0s - loss: 1.5748 - accuracy: 0.4349 2016/3595 [===============>..............] - ETA: 0s - loss: 1.5667 - accuracy: 0.4370 2176/3595 [=================>............] - ETA: 0s - loss: 1.5644 - accuracy: 0.4412 2304/3595 [==================>...........] - ETA: 0s - loss: 1.5590 - accuracy: 0.4440 2464/3595 [===================>..........] - ETA: 0s - loss: 1.5511 - accuracy: 0.4481 2592/3595 [====================>.........] - ETA: 0s - loss: 1.5539 - accuracy: 0.4479 2720/3595 [=====================>........] - ETA: 0s - loss: 1.5481 - accuracy: 0.4485 2880/3595 [=======================>......] - ETA: 0s - loss: 1.5387 - accuracy: 0.4510 3008/3595 [========================>.....] - ETA: 0s - loss: 1.5315 - accuracy: 0.4531 3168/3595 [=========================>....] - ETA: 0s - loss: 1.5249 - accuracy: 0.4549 3296/3595 [==========================>...] - ETA: 0s - loss: 1.5311 - accuracy: 0.4545 3456/3595 [===========================>..] - ETA: 0s - loss: 1.5324 - accuracy: 0.4511 3584/3595 [============================>.] - ETA: 0s - loss: 1.5336 - accuracy: 0.4509 3595/3595 [==============================] - 2s 465us/sample - loss: 1.5333 - accuracy: 0.4512 - val_loss: 1.3989 - val_accuracy: 0.4705 Epoch 5/28 32/3595 [..............................] - ETA: 3s - loss: 1.9747 - accuracy: 0.2812 192/3595 [>.............................] - ETA: 1s - loss: 1.4665 - accuracy: 0.4948 320/3595 [=>............................] - ETA: 1s - loss: 1.4924 - accuracy: 0.4938 448/3595 [==>...........................] - ETA: 1s - loss: 1.4665 - accuracy: 0.4888 576/3595 [===>..........................] - ETA: 1s - loss: 1.4635 - accuracy: 0.4878 704/3595 [====>.........................] - ETA: 1s - loss: 1.4565 - accuracy: 0.4872 832/3595 [=====>........................] - ETA: 1s - loss: 1.4602 - accuracy: 0.4724 992/3595 [=======>......................] - ETA: 1s - loss: 1.4562 - accuracy: 0.4778 1120/3595 [========>.....................] - ETA: 1s - loss: 1.4584 - accuracy: 0.4812 1216/3595 [=========>....................] - ETA: 1s - loss: 1.4438 - accuracy: 0.4877 1344/3595 [==========>...................] - ETA: 1s - loss: 1.4271 - accuracy: 0.4903 1472/3595 [===========>..................] - ETA: 1s - loss: 1.4326 - accuracy: 0.4857 1600/3595 [============>.................] - ETA: 0s - loss: 1.4265 - accuracy: 0.4888 1728/3595 [=============>................] - ETA: 0s - loss: 1.4261 - accuracy: 0.4884 1856/3595 [==============>...............] - ETA: 0s - loss: 1.4251 - accuracy: 0.4898 1984/3595 [===============>..............] - ETA: 0s - loss: 1.4267 - accuracy: 0.4894 2112/3595 [================>.............] - ETA: 0s - loss: 1.4264 - accuracy: 0.4901 2240/3595 [=================>............] - ETA: 0s - loss: 1.4278 - accuracy: 0.4884 2368/3595 [==================>...........] - ETA: 0s - loss: 1.4214 - accuracy: 0.4903 2496/3595 [===================>..........] - ETA: 0s - loss: 1.4262 - accuracy: 0.4896 2624/3595 [====================>.........] - ETA: 0s - loss: 1.4379 - accuracy: 0.4870 2752/3595 [=====================>........] - ETA: 0s - loss: 1.4340 - accuracy: 0.4858 2880/3595 [=======================>......] - ETA: 0s - loss: 1.4340 - accuracy: 0.4858 3008/3595 [========================>.....] - ETA: 0s - loss: 1.4395 - accuracy: 0.4857 3136/3595 [=========================>....] - ETA: 0s - loss: 1.4352 - accuracy: 0.4872 3264/3595 [==========================>...] - ETA: 0s - loss: 1.4318 - accuracy: 0.4887 3392/3595 [===========================>..] - ETA: 0s - loss: 1.4350 - accuracy: 0.4888 3488/3595 [============================>.] - ETA: 0s - loss: 1.4402 - accuracy: 0.4862 3595/3595 [==============================] - 2s 532us/sample - loss: 1.4390 - accuracy: 0.4871 - val_loss: 1.3385 - val_accuracy: 0.4950 Epoch 6/28 32/3595 [..............................] - ETA: 3s - loss: 1.3164 - accuracy: 0.5312 160/3595 [>.............................] - ETA: 2s - loss: 1.3611 - accuracy: 0.4875 288/3595 [=>............................] - ETA: 1s - loss: 1.3712 - accuracy: 0.5000 416/3595 [==>...........................] - ETA: 1s - loss: 1.3356 - accuracy: 0.5120 544/3595 [===>..........................] - ETA: 1s - loss: 1.3539 - accuracy: 0.5037 672/3595 [====>.........................] - ETA: 1s - loss: 1.3269 - accuracy: 0.5179 800/3595 [=====>........................] - ETA: 1s - loss: 1.3441 - accuracy: 0.5113 928/3595 [======>.......................] - ETA: 1s - loss: 1.3322 - accuracy: 0.5216 1056/3595 [=======>......................] - ETA: 1s - loss: 1.3528 - accuracy: 0.5161 1184/3595 [========>.....................] - ETA: 1s - loss: 1.3514 - accuracy: 0.5152 1312/3595 [=========>....................] - ETA: 1s - loss: 1.3588 - accuracy: 0.5160 1440/3595 [===========>..................] - ETA: 1s - loss: 1.3658 - accuracy: 0.5132 1568/3595 [============>.................] - ETA: 1s - loss: 1.3539 - accuracy: 0.5172 1696/3595 [=============>................] - ETA: 0s - loss: 1.3530 - accuracy: 0.5159 1824/3595 [==============>...............] - ETA: 0s - loss: 1.3464 - accuracy: 0.5181 1952/3595 [===============>..............] - ETA: 0s - loss: 1.3582 - accuracy: 0.5133 2080/3595 [================>.............] - ETA: 0s - loss: 1.3519 - accuracy: 0.5154 2208/3595 [=================>............] - ETA: 0s - loss: 1.3441 - accuracy: 0.5181 2336/3595 [==================>...........] - ETA: 0s - loss: 1.3406 - accuracy: 0.5210 2464/3595 [===================>..........] - ETA: 0s - loss: 1.3385 - accuracy: 0.5211 2592/3595 [====================>.........] - ETA: 0s - loss: 1.3392 - accuracy: 0.5193 2720/3595 [=====================>........] - ETA: 0s - loss: 1.3389 - accuracy: 0.5169 2848/3595 [======================>.......] - ETA: 0s - loss: 1.3474 - accuracy: 0.5147 2976/3595 [=======================>......] - ETA: 0s - loss: 1.3454 - accuracy: 0.5144 3104/3595 [========================>.....] - ETA: 0s - loss: 1.3460 - accuracy: 0.5148 3232/3595 [=========================>....] - ETA: 0s - loss: 1.3491 - accuracy: 0.5145 3360/3595 [===========================>..] - ETA: 0s - loss: 1.3504 - accuracy: 0.5137 3520/3595 [============================>.] - ETA: 0s - loss: 1.3478 - accuracy: 0.5131 3595/3595 [==============================] - 2s 522us/sample - loss: 1.3467 - accuracy: 0.5135 - val_loss: 1.2686 - val_accuracy: 0.5172 Epoch 7/28 32/3595 [..............................] - ETA: 1s - loss: 1.6148 - accuracy: 0.4062 160/3595 [>.............................] - ETA: 1s - loss: 1.3837 - accuracy: 0.4812 288/3595 [=>............................] - ETA: 1s - loss: 1.3164 - accuracy: 0.5208 416/3595 [==>...........................] - ETA: 1s - loss: 1.3066 - accuracy: 0.5361 544/3595 [===>..........................] - ETA: 1s - loss: 1.3099 - accuracy: 0.5331 672/3595 [====>.........................] - ETA: 1s - loss: 1.3047 - accuracy: 0.5402 800/3595 [=====>........................] - ETA: 1s - loss: 1.2955 - accuracy: 0.5437 928/3595 [======>.......................] - ETA: 1s - loss: 1.3105 - accuracy: 0.5356 1056/3595 [=======>......................] - ETA: 1s - loss: 1.2856 - accuracy: 0.5407 1184/3595 [========>.....................] - ETA: 1s - loss: 1.2833 - accuracy: 0.5431 1312/3595 [=========>....................] - ETA: 1s - loss: 1.2928 - accuracy: 0.5404 1440/3595 [===========>..................] - ETA: 1s - loss: 1.2964 - accuracy: 0.5431 1568/3595 [============>.................] - ETA: 1s - loss: 1.2890 - accuracy: 0.5517 1728/3595 [=============>................] - ETA: 0s - loss: 1.2915 - accuracy: 0.5446 1856/3595 [==============>...............] - ETA: 0s - loss: 1.2925 - accuracy: 0.5436 2016/3595 [===============>..............] - ETA: 0s - loss: 1.2968 - accuracy: 0.5432 2144/3595 [================>.............] - ETA: 0s - loss: 1.2925 - accuracy: 0.5457 2304/3595 [==================>...........] - ETA: 0s - loss: 1.2905 - accuracy: 0.5460 2464/3595 [===================>..........] - ETA: 0s - loss: 1.2855 - accuracy: 0.5499 2592/3595 [====================>.........] - ETA: 0s - loss: 1.2820 - accuracy: 0.5498 2752/3595 [=====================>........] - ETA: 0s - loss: 1.2758 - accuracy: 0.5512 2912/3595 [=======================>......] - ETA: 0s - loss: 1.2758 - accuracy: 0.5488 3040/3595 [========================>.....] - ETA: 0s - loss: 1.2786 - accuracy: 0.5480 3200/3595 [=========================>....] - ETA: 0s - loss: 1.2793 - accuracy: 0.5484 3360/3595 [===========================>..] - ETA: 0s - loss: 1.2805 - accuracy: 0.5479 3488/3595 [============================>.] - ETA: 0s - loss: 1.2878 - accuracy: 0.5447 3595/3595 [==============================] - 2s 488us/sample - loss: 1.2907 - accuracy: 0.5438 - val_loss: 1.2292 - val_accuracy: 0.5473 Epoch 8/28 32/3595 [..............................] - ETA: 1s - loss: 1.1152 - accuracy: 0.5312 160/3595 [>.............................] - ETA: 1s - loss: 1.2851 - accuracy: 0.5437 288/3595 [=>............................] - ETA: 1s - loss: 1.3258 - accuracy: 0.5486 416/3595 [==>...........................] - ETA: 1s - loss: 1.2697 - accuracy: 0.5481 576/3595 [===>..........................] - ETA: 1s - loss: 1.3156 - accuracy: 0.5347 704/3595 [====>.........................] - ETA: 1s - loss: 1.2861 - accuracy: 0.5469 832/3595 [=====>........................] - ETA: 1s - loss: 1.2789 - accuracy: 0.5457 960/3595 [=======>......................] - ETA: 1s - loss: 1.2721 - accuracy: 0.5469 1088/3595 [========>.....................] - ETA: 1s - loss: 1.2759 - accuracy: 0.5423 1216/3595 [=========>....................] - ETA: 1s - loss: 1.2878 - accuracy: 0.5452 1344/3595 [==========>...................] - ETA: 1s - loss: 1.2899 - accuracy: 0.5387 1472/3595 [===========>..................] - ETA: 1s - loss: 1.2847 - accuracy: 0.5414 1600/3595 [============>.................] - ETA: 0s - loss: 1.2912 - accuracy: 0.5456 1728/3595 [=============>................] - ETA: 0s - loss: 1.2925 - accuracy: 0.5451 1856/3595 [==============>...............] - ETA: 0s - loss: 1.2848 - accuracy: 0.5442 1984/3595 [===============>..............] - ETA: 0s - loss: 1.2782 - accuracy: 0.5484 2112/3595 [================>.............] - ETA: 0s - loss: 1.2698 - accuracy: 0.5516 2272/3595 [=================>............] - ETA: 0s - loss: 1.2728 - accuracy: 0.5489 2400/3595 [===================>..........] - ETA: 0s - loss: 1.2771 - accuracy: 0.5462 2528/3595 [====================>.........] - ETA: 0s - loss: 1.2776 - accuracy: 0.5471 2688/3595 [=====================>........] - ETA: 0s - loss: 1.2704 - accuracy: 0.5506 2816/3595 [======================>.......] - ETA: 0s - loss: 1.2662 - accuracy: 0.5504 2976/3595 [=======================>......] - ETA: 0s - loss: 1.2596 - accuracy: 0.5521 3104/3595 [========================>.....] - ETA: 0s - loss: 1.2584 - accuracy: 0.5535 3200/3595 [=========================>....] - ETA: 0s - loss: 1.2551 - accuracy: 0.5525 3296/3595 [==========================>...] - ETA: 0s - loss: 1.2534 - accuracy: 0.5501 3424/3595 [===========================>..] - ETA: 0s - loss: 1.2548 - accuracy: 0.5494 3520/3595 [============================>.] - ETA: 0s - loss: 1.2513 - accuracy: 0.5489 3595/3595 [==============================] - 2s 513us/sample - loss: 1.2497 - accuracy: 0.5488 - val_loss: 1.1831 - val_accuracy: 0.5628 Epoch 9/28 32/3595 [..............................] - ETA: 1s - loss: 1.1221 - accuracy: 0.6250 192/3595 [>.............................] - ETA: 1s - loss: 1.1909 - accuracy: 0.5833 320/3595 [=>............................] - ETA: 1s - loss: 1.1968 - accuracy: 0.5719 480/3595 [===>..........................] - ETA: 1s - loss: 1.1625 - accuracy: 0.5875 608/3595 [====>.........................] - ETA: 1s - loss: 1.2070 - accuracy: 0.5789 736/3595 [=====>........................] - ETA: 1s - loss: 1.2055 - accuracy: 0.5802 896/3595 [======>.......................] - ETA: 1s - loss: 1.2294 - accuracy: 0.5681 1024/3595 [=======>......................] - ETA: 1s - loss: 1.2322 - accuracy: 0.5723 1184/3595 [========>.....................] - ETA: 1s - loss: 1.2208 - accuracy: 0.5735 1312/3595 [=========>....................] - ETA: 1s - loss: 1.2140 - accuracy: 0.5762 1472/3595 [===========>..................] - ETA: 0s - loss: 1.2315 - accuracy: 0.5707 1600/3595 [============>.................] - ETA: 0s - loss: 1.2282 - accuracy: 0.5688 1760/3595 [=============>................] - ETA: 0s - loss: 1.2303 - accuracy: 0.5676 1888/3595 [==============>...............] - ETA: 0s - loss: 1.2237 - accuracy: 0.5699 2016/3595 [===============>..............] - ETA: 0s - loss: 1.2219 - accuracy: 0.5680 2176/3595 [=================>............] - ETA: 0s - loss: 1.2149 - accuracy: 0.5708 2304/3595 [==================>...........] - ETA: 0s - loss: 1.2156 - accuracy: 0.5694 2464/3595 [===================>..........] - ETA: 0s - loss: 1.2130 - accuracy: 0.5670 2592/3595 [====================>.........] - ETA: 0s - loss: 1.2149 - accuracy: 0.5675 2752/3595 [=====================>........] - ETA: 0s - loss: 1.2197 - accuracy: 0.5654 2880/3595 [=======================>......] - ETA: 0s - loss: 1.2149 - accuracy: 0.5684 3008/3595 [========================>.....] - ETA: 0s - loss: 1.2184 - accuracy: 0.5685 3104/3595 [========================>.....] - ETA: 0s - loss: 1.2125 - accuracy: 0.5702 3232/3595 [=========================>....] - ETA: 0s - loss: 1.2127 - accuracy: 0.5693 3360/3595 [===========================>..] - ETA: 0s - loss: 1.2188 - accuracy: 0.5673 3488/3595 [============================>.] - ETA: 0s - loss: 1.2128 - accuracy: 0.5685 3584/3595 [============================>.] - ETA: 0s - loss: 1.2161 - accuracy: 0.5661 3595/3595 [==============================] - 2s 488us/sample - loss: 1.2153 - accuracy: 0.5661 - val_loss: 1.1730 - val_accuracy: 0.5840 Epoch 10/28 32/3595 [..............................] - ETA: 1s - loss: 1.0482 - accuracy: 0.7188 160/3595 [>.............................] - ETA: 1s - loss: 1.1542 - accuracy: 0.6125 288/3595 [=>............................] - ETA: 1s - loss: 1.0607 - accuracy: 0.6146 416/3595 [==>...........................] - ETA: 1s - loss: 1.0499 - accuracy: 0.6202 544/3595 [===>..........................] - ETA: 1s - loss: 1.0425 - accuracy: 0.6324 672/3595 [====>.........................] - ETA: 1s - loss: 1.0630 - accuracy: 0.6235 800/3595 [=====>........................] - ETA: 1s - loss: 1.0591 - accuracy: 0.6263 928/3595 [======>.......................] - ETA: 1s - loss: 1.0740 - accuracy: 0.6088 1056/3595 [=======>......................] - ETA: 1s - loss: 1.0895 - accuracy: 0.6042 1184/3595 [========>.....................] - ETA: 1s - loss: 1.0924 - accuracy: 0.5963 1312/3595 [=========>....................] - ETA: 1s - loss: 1.0825 - accuracy: 0.6021 1440/3595 [===========>..................] - ETA: 1s - loss: 1.0848 - accuracy: 0.5993 1568/3595 [============>.................] - ETA: 1s - loss: 1.0942 - accuracy: 0.5982 1696/3595 [=============>................] - ETA: 0s - loss: 1.1031 - accuracy: 0.5955 1824/3595 [==============>...............] - ETA: 0s - loss: 1.1276 - accuracy: 0.5855 1952/3595 [===============>..............] - ETA: 0s - loss: 1.1320 - accuracy: 0.5830 2048/3595 [================>.............] - ETA: 0s - loss: 1.1519 - accuracy: 0.5776 2176/3595 [=================>............] - ETA: 0s - loss: 1.1492 - accuracy: 0.5754 2304/3595 [==================>...........] - ETA: 0s - loss: 1.1476 - accuracy: 0.5777 2432/3595 [===================>..........] - ETA: 0s - loss: 1.1497 - accuracy: 0.5769 2560/3595 [====================>.........] - ETA: 0s - loss: 1.1495 - accuracy: 0.5781 2688/3595 [=====================>........] - ETA: 0s - loss: 1.1499 - accuracy: 0.5774 2816/3595 [======================>.......] - ETA: 0s - loss: 1.1533 - accuracy: 0.5774 2944/3595 [=======================>......] - ETA: 0s - loss: 1.1550 - accuracy: 0.5781 3072/3595 [========================>.....] - ETA: 0s - loss: 1.1570 - accuracy: 0.5781 3200/3595 [=========================>....] - ETA: 0s - loss: 1.1572 - accuracy: 0.5772 3328/3595 [==========================>...] - ETA: 0s - loss: 1.1679 - accuracy: 0.5730 3456/3595 [===========================>..] - ETA: 0s - loss: 1.1699 - accuracy: 0.5726 3584/3595 [============================>.] - ETA: 0s - loss: 1.1646 - accuracy: 0.5737 3595/3595 [==============================] - 2s 530us/sample - loss: 1.1630 - accuracy: 0.5744 - val_loss: 1.1515 - val_accuracy: 0.5895 Epoch 11/28 32/3595 [..............................] - ETA: 1s - loss: 0.7909 - accuracy: 0.7500 160/3595 [>.............................] - ETA: 1s - loss: 1.0469 - accuracy: 0.6687 256/3595 [=>............................] - ETA: 1s - loss: 1.0856 - accuracy: 0.6406 384/3595 [==>...........................] - ETA: 1s - loss: 1.1384 - accuracy: 0.6250 512/3595 [===>..........................] - ETA: 1s - loss: 1.1088 - accuracy: 0.6211 640/3595 [====>.........................] - ETA: 1s - loss: 1.1373 - accuracy: 0.6187 768/3595 [=====>........................] - ETA: 1s - loss: 1.1295 - accuracy: 0.6159 896/3595 [======>.......................] - ETA: 1s - loss: 1.1099 - accuracy: 0.6239 1024/3595 [=======>......................] - ETA: 1s - loss: 1.0956 - accuracy: 0.6299 1152/3595 [========>.....................] - ETA: 1s - loss: 1.1086 - accuracy: 0.6198 1280/3595 [=========>....................] - ETA: 1s - loss: 1.1102 - accuracy: 0.6133 1376/3595 [==========>...................] - ETA: 1s - loss: 1.1110 - accuracy: 0.6112 1536/3595 [===========>..................] - ETA: 1s - loss: 1.1102 - accuracy: 0.6094 1696/3595 [=============>................] - ETA: 0s - loss: 1.1106 - accuracy: 0.6044 1824/3595 [==============>...............] - ETA: 0s - loss: 1.1113 - accuracy: 0.6009 1984/3595 [===============>..............] - ETA: 0s - loss: 1.1183 - accuracy: 0.6028 2144/3595 [================>.............] - ETA: 0s - loss: 1.1171 - accuracy: 0.5998 2304/3595 [==================>...........] - ETA: 0s - loss: 1.1131 - accuracy: 0.5985 2432/3595 [===================>..........] - ETA: 0s - loss: 1.1066 - accuracy: 0.6020 2592/3595 [====================>.........] - ETA: 0s - loss: 1.0997 - accuracy: 0.6022 2720/3595 [=====================>........] - ETA: 0s - loss: 1.0994 - accuracy: 0.6015 2848/3595 [======================>.......] - ETA: 0s - loss: 1.1004 - accuracy: 0.6018 2944/3595 [=======================>......] - ETA: 0s - loss: 1.0979 - accuracy: 0.6016 3072/3595 [========================>.....] - ETA: 0s - loss: 1.0917 - accuracy: 0.6061 3168/3595 [=========================>....] - ETA: 0s - loss: 1.0902 - accuracy: 0.6061 3296/3595 [==========================>...] - ETA: 0s - loss: 1.0971 - accuracy: 0.6041 3424/3595 [===========================>..] - ETA: 0s - loss: 1.0982 - accuracy: 0.6043 3584/3595 [============================>.] - ETA: 0s - loss: 1.0992 - accuracy: 0.6018 3595/3595 [==============================] - 2s 502us/sample - loss: 1.0991 - accuracy: 0.6019 - val_loss: 1.1378 - val_accuracy: 0.5940 Epoch 12/28 32/3595 [..............................] - ETA: 1s - loss: 0.7917 - accuracy: 0.6875 192/3595 [>.............................] - ETA: 1s - loss: 0.9069 - accuracy: 0.6667 320/3595 [=>............................] - ETA: 1s - loss: 1.0410 - accuracy: 0.6313 448/3595 [==>...........................] - ETA: 1s - loss: 1.0619 - accuracy: 0.6116 576/3595 [===>..........................] - ETA: 1s - loss: 1.0799 - accuracy: 0.6111 704/3595 [====>.........................] - ETA: 1s - loss: 1.0696 - accuracy: 0.6151 832/3595 [=====>........................] - ETA: 1s - loss: 1.0792 - accuracy: 0.6178 992/3595 [=======>......................] - ETA: 1s - loss: 1.0805 - accuracy: 0.6119 1120/3595 [========>.....................] - ETA: 1s - loss: 1.1003 - accuracy: 0.6054 1248/3595 [=========>....................] - ETA: 1s - loss: 1.0873 - accuracy: 0.6106 1344/3595 [==========>...................] - ETA: 1s - loss: 1.0761 - accuracy: 0.6161 1504/3595 [===========>..................] - ETA: 0s - loss: 1.0749 - accuracy: 0.6144 1632/3595 [============>.................] - ETA: 0s - loss: 1.0773 - accuracy: 0.6170 1760/3595 [=============>................] - ETA: 0s - loss: 1.0816 - accuracy: 0.6148 1888/3595 [==============>...............] - ETA: 0s - loss: 1.0836 - accuracy: 0.6128 2016/3595 [===============>..............] - ETA: 0s - loss: 1.0805 - accuracy: 0.6166 2144/3595 [================>.............] - ETA: 0s - loss: 1.0726 - accuracy: 0.6185 2272/3595 [=================>............] - ETA: 0s - loss: 1.0714 - accuracy: 0.6188 2432/3595 [===================>..........] - ETA: 0s - loss: 1.0647 - accuracy: 0.6213 2560/3595 [====================>.........] - ETA: 0s - loss: 1.0627 - accuracy: 0.6207 2688/3595 [=====================>........] - ETA: 0s - loss: 1.0592 - accuracy: 0.6217 2816/3595 [======================>.......] - ETA: 0s - loss: 1.0603 - accuracy: 0.6222 2944/3595 [=======================>......] - ETA: 0s - loss: 1.0544 - accuracy: 0.6243 3072/3595 [========================>.....] - ETA: 0s - loss: 1.0601 - accuracy: 0.6224 3232/3595 [=========================>....] - ETA: 0s - loss: 1.0604 - accuracy: 0.6235 3360/3595 [===========================>..] - ETA: 0s - loss: 1.0602 - accuracy: 0.6244 3488/3595 [============================>.] - ETA: 0s - loss: 1.0591 - accuracy: 0.6239 3595/3595 [==============================] - 2s 498us/sample - loss: 1.0619 - accuracy: 0.6217 - val_loss: 1.1014 - val_accuracy: 0.6085 Epoch 13/28 32/3595 [..............................] - ETA: 1s - loss: 0.9791 - accuracy: 0.5938 160/3595 [>.............................] - ETA: 1s - loss: 1.2249 - accuracy: 0.5750 288/3595 [=>............................] - ETA: 1s - loss: 1.1139 - accuracy: 0.6076 448/3595 [==>...........................] - ETA: 1s - loss: 1.0495 - accuracy: 0.6295 576/3595 [===>..........................] - ETA: 1s - loss: 1.0485 - accuracy: 0.6146 704/3595 [====>.........................] - ETA: 1s - loss: 1.0537 - accuracy: 0.6122 832/3595 [=====>........................] - ETA: 1s - loss: 1.0267 - accuracy: 0.6250 960/3595 [=======>......................] - ETA: 1s - loss: 1.0223 - accuracy: 0.6281 1088/3595 [========>.....................] - ETA: 1s - loss: 1.0501 - accuracy: 0.6176 1248/3595 [=========>....................] - ETA: 1s - loss: 1.0499 - accuracy: 0.6122 1376/3595 [==========>...................] - ETA: 1s - loss: 1.0324 - accuracy: 0.6206 1504/3595 [===========>..................] - ETA: 0s - loss: 1.0439 - accuracy: 0.6184 1632/3595 [============>.................] - ETA: 0s - loss: 1.0499 - accuracy: 0.6183 1760/3595 [=============>................] - ETA: 0s - loss: 1.0523 - accuracy: 0.6148 1888/3595 [==============>...............] - ETA: 0s - loss: 1.0526 - accuracy: 0.6171 2016/3595 [===============>..............] - ETA: 0s - loss: 1.0415 - accuracy: 0.6235 2144/3595 [================>.............] - ETA: 0s - loss: 1.0420 - accuracy: 0.6217 2272/3595 [=================>............] - ETA: 0s - loss: 1.0482 - accuracy: 0.6215 2368/3595 [==================>...........] - ETA: 0s - loss: 1.0447 - accuracy: 0.6242 2496/3595 [===================>..........] - ETA: 0s - loss: 1.0497 - accuracy: 0.6210 2624/3595 [====================>.........] - ETA: 0s - loss: 1.0529 - accuracy: 0.6181 2784/3595 [======================>.......] - ETA: 0s - loss: 1.0505 - accuracy: 0.6196 2880/3595 [=======================>......] - ETA: 0s - loss: 1.0523 - accuracy: 0.6187 3008/3595 [========================>.....] - ETA: 0s - loss: 1.0507 - accuracy: 0.6203 3168/3595 [=========================>....] - ETA: 0s - loss: 1.0488 - accuracy: 0.6209 3296/3595 [==========================>...] - ETA: 0s - loss: 1.0472 - accuracy: 0.6198 3424/3595 [===========================>..] - ETA: 0s - loss: 1.0469 - accuracy: 0.6197 3552/3595 [============================>.] - ETA: 0s - loss: 1.0464 - accuracy: 0.6213 3595/3595 [==============================] - 2s 510us/sample - loss: 1.0489 - accuracy: 0.6200 - val_loss: 1.0823 - val_accuracy: 0.6007 Epoch 14/28 32/3595 [..............................] - ETA: 1s - loss: 1.0709 - accuracy: 0.6250 160/3595 [>.............................] - ETA: 1s - loss: 1.3093 - accuracy: 0.5312 288/3595 [=>............................] - ETA: 1s - loss: 1.1947 - accuracy: 0.5694 416/3595 [==>...........................] - ETA: 1s - loss: 1.1569 - accuracy: 0.5865 544/3595 [===>..........................] - ETA: 1s - loss: 1.1280 - accuracy: 0.6029 672/3595 [====>.........................] - ETA: 1s - loss: 1.1140 - accuracy: 0.6027 800/3595 [=====>........................] - ETA: 1s - loss: 1.0940 - accuracy: 0.6012 928/3595 [======>.......................] - ETA: 1s - loss: 1.0804 - accuracy: 0.6067 1056/3595 [=======>......................] - ETA: 1s - loss: 1.1158 - accuracy: 0.6013 1184/3595 [========>.....................] - ETA: 1s - loss: 1.1089 - accuracy: 0.6005 1312/3595 [=========>....................] - ETA: 1s - loss: 1.0915 - accuracy: 0.6059 1440/3595 [===========>..................] - ETA: 1s - loss: 1.0823 - accuracy: 0.6076 1568/3595 [============>.................] - ETA: 1s - loss: 1.0686 - accuracy: 0.6148 1696/3595 [=============>................] - ETA: 0s - loss: 1.0705 - accuracy: 0.6114 1824/3595 [==============>...............] - ETA: 0s - loss: 1.0583 - accuracy: 0.6168 1952/3595 [===============>..............] - ETA: 0s - loss: 1.0600 - accuracy: 0.6199 2080/3595 [================>.............] - ETA: 0s - loss: 1.0541 - accuracy: 0.6226 2208/3595 [=================>............] - ETA: 0s - loss: 1.0487 - accuracy: 0.6255 2336/3595 [==================>...........] - ETA: 0s - loss: 1.0474 - accuracy: 0.6246 2432/3595 [===================>..........] - ETA: 0s - loss: 1.0461 - accuracy: 0.6283 2528/3595 [====================>.........] - ETA: 0s - loss: 1.0506 - accuracy: 0.6254 2656/3595 [=====================>........] - ETA: 0s - loss: 1.0487 - accuracy: 0.6246 2784/3595 [======================>.......] - ETA: 0s - loss: 1.0440 - accuracy: 0.6264 2880/3595 [=======================>......] - ETA: 0s - loss: 1.0425 - accuracy: 0.6288 3008/3595 [========================>.....] - ETA: 0s - loss: 1.0370 - accuracy: 0.6283 3136/3595 [=========================>....] - ETA: 0s - loss: 1.0342 - accuracy: 0.6285 3264/3595 [==========================>...] - ETA: 0s - loss: 1.0267 - accuracy: 0.6314 3392/3595 [===========================>..] - ETA: 0s - loss: 1.0218 - accuracy: 0.6338 3520/3595 [============================>.] - ETA: 0s - loss: 1.0150 - accuracy: 0.6361 3595/3595 [==============================] - 2s 539us/sample - loss: 1.0145 - accuracy: 0.6362 - val_loss: 1.0772 - val_accuracy: 0.6218 Epoch 15/28 32/3595 [..............................] - ETA: 3s - loss: 1.2261 - accuracy: 0.6562 160/3595 [>.............................] - ETA: 2s - loss: 0.9936 - accuracy: 0.6687 288/3595 [=>............................] - ETA: 1s - loss: 1.0020 - accuracy: 0.6528 416/3595 [==>...........................] - ETA: 1s - loss: 1.0033 - accuracy: 0.6466 544/3595 [===>..........................] - ETA: 1s - loss: 0.9955 - accuracy: 0.6397 640/3595 [====>.........................] - ETA: 1s - loss: 1.0174 - accuracy: 0.6266 768/3595 [=====>........................] - ETA: 1s - loss: 1.0043 - accuracy: 0.6289 896/3595 [======>.......................] - ETA: 1s - loss: 0.9889 - accuracy: 0.6395 1024/3595 [=======>......................] - ETA: 1s - loss: 0.9628 - accuracy: 0.6533 1152/3595 [========>.....................] - ETA: 1s - loss: 0.9679 - accuracy: 0.6484 1280/3595 [=========>....................] - ETA: 1s - loss: 0.9797 - accuracy: 0.6469 1376/3595 [==========>...................] - ETA: 1s - loss: 0.9917 - accuracy: 0.6432 1504/3595 [===========>..................] - ETA: 1s - loss: 0.9871 - accuracy: 0.6469 1632/3595 [============>.................] - ETA: 1s - loss: 0.9806 - accuracy: 0.6464 1760/3595 [=============>................] - ETA: 0s - loss: 0.9741 - accuracy: 0.6517 1888/3595 [==============>...............] - ETA: 0s - loss: 0.9774 - accuracy: 0.6510 2016/3595 [===============>..............] - ETA: 0s - loss: 0.9743 - accuracy: 0.6548 2144/3595 [================>.............] - ETA: 0s - loss: 0.9833 - accuracy: 0.6521 2240/3595 [=================>............] - ETA: 0s - loss: 0.9764 - accuracy: 0.6562 2400/3595 [===================>..........] - ETA: 0s - loss: 0.9805 - accuracy: 0.6550 2528/3595 [====================>.........] - ETA: 0s - loss: 0.9771 - accuracy: 0.6590 2688/3595 [=====================>........] - ETA: 0s - loss: 0.9710 - accuracy: 0.6600 2816/3595 [======================>.......] - ETA: 0s - loss: 0.9718 - accuracy: 0.6609 2976/3595 [=======================>......] - ETA: 0s - loss: 0.9784 - accuracy: 0.6562 3104/3595 [========================>.....] - ETA: 0s - loss: 0.9835 - accuracy: 0.6534 3264/3595 [==========================>...] - ETA: 0s - loss: 0.9786 - accuracy: 0.6547 3424/3595 [===========================>..] - ETA: 0s - loss: 0.9830 - accuracy: 0.6548 3552/3595 [============================>.] - ETA: 0s - loss: 0.9791 - accuracy: 0.6551 3595/3595 [==============================] - 2s 512us/sample - loss: 0.9783 - accuracy: 0.6545 - val_loss: 1.0756 - val_accuracy: 0.6062 Epoch 16/28 32/3595 [..............................] - ETA: 1s - loss: 0.7781 - accuracy: 0.6250 160/3595 [>.............................] - ETA: 1s - loss: 0.8862 - accuracy: 0.6375 256/3595 [=>............................] - ETA: 1s - loss: 0.9073 - accuracy: 0.6445 416/3595 [==>...........................] - ETA: 1s - loss: 0.8900 - accuracy: 0.6683 544/3595 [===>..........................] - ETA: 1s - loss: 0.8832 - accuracy: 0.6765 672/3595 [====>.........................] - ETA: 1s - loss: 0.9112 - accuracy: 0.6667 832/3595 [=====>........................] - ETA: 1s - loss: 0.9195 - accuracy: 0.6647 960/3595 [=======>......................] - ETA: 1s - loss: 0.9200 - accuracy: 0.6656 1120/3595 [========>.....................] - ETA: 1s - loss: 0.9266 - accuracy: 0.6625 1248/3595 [=========>....................] - ETA: 1s - loss: 0.9353 - accuracy: 0.6643 1376/3595 [==========>...................] - ETA: 1s - loss: 0.9396 - accuracy: 0.6642 1536/3595 [===========>..................] - ETA: 0s - loss: 0.9486 - accuracy: 0.6621 1664/3595 [============>.................] - ETA: 0s - loss: 0.9423 - accuracy: 0.6647 1824/3595 [==============>...............] - ETA: 0s - loss: 0.9531 - accuracy: 0.6606 1952/3595 [===============>..............] - ETA: 0s - loss: 0.9518 - accuracy: 0.6614 2080/3595 [================>.............] - ETA: 0s - loss: 0.9439 - accuracy: 0.6663 2240/3595 [=================>............] - ETA: 0s - loss: 0.9427 - accuracy: 0.6665 2368/3595 [==================>...........] - ETA: 0s - loss: 0.9379 - accuracy: 0.6681 2496/3595 [===================>..........] - ETA: 0s - loss: 0.9372 - accuracy: 0.6659 2656/3595 [=====================>........] - ETA: 0s - loss: 0.9404 - accuracy: 0.6642 2784/3595 [======================>.......] - ETA: 0s - loss: 0.9385 - accuracy: 0.6645 2944/3595 [=======================>......] - ETA: 0s - loss: 0.9460 - accuracy: 0.6603 3072/3595 [========================>.....] - ETA: 0s - loss: 0.9497 - accuracy: 0.6589 3200/3595 [=========================>....] - ETA: 0s - loss: 0.9409 - accuracy: 0.6637 3328/3595 [==========================>...] - ETA: 0s - loss: 0.9376 - accuracy: 0.6662 3456/3595 [===========================>..] - ETA: 0s - loss: 0.9487 - accuracy: 0.6632 3584/3595 [============================>.] - ETA: 0s - loss: 0.9433 - accuracy: 0.6646 3595/3595 [==============================] - 2s 487us/sample - loss: 0.9442 - accuracy: 0.6640 - val_loss: 1.0457 - val_accuracy: 0.6162 Epoch 17/28 32/3595 [..............................] - ETA: 1s - loss: 0.7290 - accuracy: 0.7188 160/3595 [>.............................] - ETA: 1s - loss: 0.7861 - accuracy: 0.7375 288/3595 [=>............................] - ETA: 1s - loss: 0.8436 - accuracy: 0.6910 416/3595 [==>...........................] - ETA: 1s - loss: 0.8752 - accuracy: 0.6731 512/3595 [===>..........................] - ETA: 1s - loss: 0.9229 - accuracy: 0.6641 640/3595 [====>.........................] - ETA: 1s - loss: 0.9062 - accuracy: 0.6703 768/3595 [=====>........................] - ETA: 1s - loss: 0.8950 - accuracy: 0.6719 896/3595 [======>.......................] - ETA: 1s - loss: 0.9090 - accuracy: 0.6663 1024/3595 [=======>......................] - ETA: 1s - loss: 0.9089 - accuracy: 0.6719 1152/3595 [========>.....................] - ETA: 1s - loss: 0.9055 - accuracy: 0.6762 1280/3595 [=========>....................] - ETA: 1s - loss: 0.9071 - accuracy: 0.6766 1376/3595 [==========>...................] - ETA: 1s - loss: 0.9132 - accuracy: 0.6737 1504/3595 [===========>..................] - ETA: 1s - loss: 0.9184 - accuracy: 0.6729 1632/3595 [============>.................] - ETA: 0s - loss: 0.9162 - accuracy: 0.6752 1760/3595 [=============>................] - ETA: 0s - loss: 0.9127 - accuracy: 0.6756 1888/3595 [==============>...............] - ETA: 0s - loss: 0.9178 - accuracy: 0.6732 2016/3595 [===============>..............] - ETA: 0s - loss: 0.9200 - accuracy: 0.6736 2144/3595 [================>.............] - ETA: 0s - loss: 0.9095 - accuracy: 0.6791 2272/3595 [=================>............] - ETA: 0s - loss: 0.9030 - accuracy: 0.6813 2400/3595 [===================>..........] - ETA: 0s - loss: 0.9044 - accuracy: 0.6804 2496/3595 [===================>..........] - ETA: 0s - loss: 0.9104 - accuracy: 0.6779 2624/3595 [====================>.........] - ETA: 0s - loss: 0.9077 - accuracy: 0.6795 2752/3595 [=====================>........] - ETA: 0s - loss: 0.9127 - accuracy: 0.6770 2912/3595 [=======================>......] - ETA: 0s - loss: 0.9090 - accuracy: 0.6796 3040/3595 [========================>.....] - ETA: 0s - loss: 0.9051 - accuracy: 0.6806 3168/3595 [=========================>....] - ETA: 0s - loss: 0.9110 - accuracy: 0.6793 3296/3595 [==========================>...] - ETA: 0s - loss: 0.9169 - accuracy: 0.6775 3424/3595 [===========================>..] - ETA: 0s - loss: 0.9151 - accuracy: 0.6764 3552/3595 [============================>.] - ETA: 0s - loss: 0.9165 - accuracy: 0.6771 3595/3595 [==============================] - 2s 542us/sample - loss: 0.9184 - accuracy: 0.6759 - val_loss: 1.0365 - val_accuracy: 0.6329 Epoch 18/28 32/3595 [..............................] - ETA: 1s - loss: 1.0212 - accuracy: 0.5938 128/3595 [>.............................] - ETA: 2s - loss: 0.8724 - accuracy: 0.6797 256/3595 [=>............................] - ETA: 1s - loss: 0.9408 - accuracy: 0.6523 384/3595 [==>...........................] - ETA: 1s - loss: 0.9328 - accuracy: 0.6510 512/3595 [===>..........................] - ETA: 1s - loss: 0.9326 - accuracy: 0.6484 640/3595 [====>.........................] - ETA: 1s - loss: 0.9096 - accuracy: 0.6578 768/3595 [=====>........................] - ETA: 1s - loss: 0.8943 - accuracy: 0.6667 896/3595 [======>.......................] - ETA: 1s - loss: 0.9038 - accuracy: 0.6663 1024/3595 [=======>......................] - ETA: 1s - loss: 0.8961 - accuracy: 0.6699 1152/3595 [========>.....................] - ETA: 1s - loss: 0.8719 - accuracy: 0.6840 1280/3595 [=========>....................] - ETA: 1s - loss: 0.8928 - accuracy: 0.6789 1408/3595 [==========>...................] - ETA: 1s - loss: 0.8831 - accuracy: 0.6847 1536/3595 [===========>..................] - ETA: 1s - loss: 0.8868 - accuracy: 0.6855 1664/3595 [============>.................] - ETA: 0s - loss: 0.8818 - accuracy: 0.6887 1792/3595 [=============>................] - ETA: 0s - loss: 0.8806 - accuracy: 0.6908 1920/3595 [===============>..............] - ETA: 0s - loss: 0.8832 - accuracy: 0.6859 2048/3595 [================>.............] - ETA: 0s - loss: 0.8932 - accuracy: 0.6821 2176/3595 [=================>............] - ETA: 0s - loss: 0.8875 - accuracy: 0.6852 2304/3595 [==================>...........] - ETA: 0s - loss: 0.8842 - accuracy: 0.6879 2432/3595 [===================>..........] - ETA: 0s - loss: 0.8817 - accuracy: 0.6916 2560/3595 [====================>.........] - ETA: 0s - loss: 0.8795 - accuracy: 0.6918 2688/3595 [=====================>........] - ETA: 0s - loss: 0.8843 - accuracy: 0.6901 2816/3595 [======================>.......] - ETA: 0s - loss: 0.8827 - accuracy: 0.6907 2944/3595 [=======================>......] - ETA: 0s - loss: 0.8832 - accuracy: 0.6895 3072/3595 [========================>.....] - ETA: 0s - loss: 0.8847 - accuracy: 0.6895 3200/3595 [=========================>....] - ETA: 0s - loss: 0.8810 - accuracy: 0.6900 3328/3595 [==========================>...] - ETA: 0s - loss: 0.8801 - accuracy: 0.6896 3456/3595 [===========================>..] - ETA: 0s - loss: 0.8817 - accuracy: 0.6904 3584/3595 [============================>.] - ETA: 0s - loss: 0.8792 - accuracy: 0.6908 3595/3595 [==============================] - 2s 521us/sample - loss: 0.8796 - accuracy: 0.6907 - val_loss: 1.0090 - val_accuracy: 0.6329 Epoch 19/28 32/3595 [..............................] - ETA: 1s - loss: 1.1339 - accuracy: 0.5000 160/3595 [>.............................] - ETA: 1s - loss: 1.0085 - accuracy: 0.6438 288/3595 [=>............................] - ETA: 1s - loss: 0.9235 - accuracy: 0.6736 416/3595 [==>...........................] - ETA: 1s - loss: 0.8756 - accuracy: 0.6875 544/3595 [===>..........................] - ETA: 1s - loss: 0.8481 - accuracy: 0.7096 672/3595 [====>.........................] - ETA: 1s - loss: 0.8410 - accuracy: 0.7113 800/3595 [=====>........................] - ETA: 1s - loss: 0.8258 - accuracy: 0.7138 928/3595 [======>.......................] - ETA: 1s - loss: 0.8404 - accuracy: 0.7134 1056/3595 [=======>......................] - ETA: 1s - loss: 0.8385 - accuracy: 0.7121 1152/3595 [========>.....................] - ETA: 1s - loss: 0.8504 - accuracy: 0.7075 1280/3595 [=========>....................] - ETA: 1s - loss: 0.8626 - accuracy: 0.7023 1408/3595 [==========>...................] - ETA: 1s - loss: 0.8617 - accuracy: 0.7045 1536/3595 [===========>..................] - ETA: 1s - loss: 0.8570 - accuracy: 0.7064 1664/3595 [============>.................] - ETA: 0s - loss: 0.8616 - accuracy: 0.7037 1792/3595 [=============>................] - ETA: 0s - loss: 0.8582 - accuracy: 0.7070 1920/3595 [===============>..............] - ETA: 0s - loss: 0.8610 - accuracy: 0.7047 2048/3595 [================>.............] - ETA: 0s - loss: 0.8688 - accuracy: 0.7026 2176/3595 [=================>............] - ETA: 0s - loss: 0.8677 - accuracy: 0.7036 2304/3595 [==================>...........] - ETA: 0s - loss: 0.8597 - accuracy: 0.7066 2400/3595 [===================>..........] - ETA: 0s - loss: 0.8565 - accuracy: 0.7079 2528/3595 [====================>.........] - ETA: 0s - loss: 0.8621 - accuracy: 0.7069 2656/3595 [=====================>........] - ETA: 0s - loss: 0.8524 - accuracy: 0.7105 2784/3595 [======================>.......] - ETA: 0s - loss: 0.8472 - accuracy: 0.7130 2912/3595 [=======================>......] - ETA: 0s - loss: 0.8454 - accuracy: 0.7143 3040/3595 [========================>.....] - ETA: 0s - loss: 0.8472 - accuracy: 0.7125 3168/3595 [=========================>....] - ETA: 0s - loss: 0.8451 - accuracy: 0.7137 3296/3595 [==========================>...] - ETA: 0s - loss: 0.8369 - accuracy: 0.7169 3424/3595 [===========================>..] - ETA: 0s - loss: 0.8412 - accuracy: 0.7147 3552/3595 [============================>.] - ETA: 0s - loss: 0.8380 - accuracy: 0.7137 3595/3595 [==============================] - 2s 530us/sample - loss: 0.8438 - accuracy: 0.7115 - val_loss: 1.0022 - val_accuracy: 0.6407 Epoch 20/28 32/3595 [..............................] - ETA: 1s - loss: 0.6809 - accuracy: 0.7500 160/3595 [>.............................] - ETA: 1s - loss: 0.9014 - accuracy: 0.7000 288/3595 [=>............................] - ETA: 1s - loss: 0.8932 - accuracy: 0.7049 416/3595 [==>...........................] - ETA: 1s - loss: 0.8630 - accuracy: 0.7091 544/3595 [===>..........................] - ETA: 1s - loss: 0.8631 - accuracy: 0.7059 672/3595 [====>.........................] - ETA: 1s - loss: 0.8497 - accuracy: 0.7083 800/3595 [=====>........................] - ETA: 1s - loss: 0.8526 - accuracy: 0.7000 928/3595 [======>.......................] - ETA: 1s - loss: 0.8233 - accuracy: 0.7101 1024/3595 [=======>......................] - ETA: 1s - loss: 0.8318 - accuracy: 0.7070 1152/3595 [========>.....................] - ETA: 1s - loss: 0.8338 - accuracy: 0.7057 1248/3595 [=========>....................] - ETA: 1s - loss: 0.8425 - accuracy: 0.7019 1344/3595 [==========>...................] - ETA: 1s - loss: 0.8429 - accuracy: 0.7009 1440/3595 [===========>..................] - ETA: 1s - loss: 0.8477 - accuracy: 0.6965 1536/3595 [===========>..................] - ETA: 1s - loss: 0.8502 - accuracy: 0.6960 1632/3595 [============>.................] - ETA: 1s - loss: 0.8450 - accuracy: 0.6985 1760/3595 [=============>................] - ETA: 1s - loss: 0.8437 - accuracy: 0.7000 1888/3595 [==============>...............] - ETA: 0s - loss: 0.8436 - accuracy: 0.7013 2048/3595 [================>.............] - ETA: 0s - loss: 0.8545 - accuracy: 0.6982 2176/3595 [=================>............] - ETA: 0s - loss: 0.8557 - accuracy: 0.6976 2304/3595 [==================>...........] - ETA: 0s - loss: 0.8471 - accuracy: 0.7005 2432/3595 [===================>..........] - ETA: 0s - loss: 0.8436 - accuracy: 0.7011 2560/3595 [====================>.........] - ETA: 0s - loss: 0.8439 - accuracy: 0.7004 2688/3595 [=====================>........] - ETA: 0s - loss: 0.8408 - accuracy: 0.7050 2816/3595 [======================>.......] - ETA: 0s - loss: 0.8331 - accuracy: 0.7088 2944/3595 [=======================>......] - ETA: 0s - loss: 0.8322 - accuracy: 0.7082 3072/3595 [========================>.....] - ETA: 0s - loss: 0.8344 - accuracy: 0.7067 3200/3595 [=========================>....] - ETA: 0s - loss: 0.8400 - accuracy: 0.7041 3296/3595 [==========================>...] - ETA: 0s - loss: 0.8362 - accuracy: 0.7051 3424/3595 [===========================>..] - ETA: 0s - loss: 0.8338 - accuracy: 0.7056 3552/3595 [============================>.] - ETA: 0s - loss: 0.8324 - accuracy: 0.7066 3595/3595 [==============================] - 2s 548us/sample - loss: 0.8322 - accuracy: 0.7065 - val_loss: 1.0225 - val_accuracy: 0.6474 Epoch 21/28 32/3595 [..............................] - ETA: 1s - loss: 1.0594 - accuracy: 0.7188 128/3595 [>.............................] - ETA: 2s - loss: 0.9304 - accuracy: 0.6406 256/3595 [=>............................] - ETA: 1s - loss: 0.8611 - accuracy: 0.6797 384/3595 [==>...........................] - ETA: 1s - loss: 0.8137 - accuracy: 0.6953 512/3595 [===>..........................] - ETA: 1s - loss: 0.8221 - accuracy: 0.7051 640/3595 [====>.........................] - ETA: 1s - loss: 0.8075 - accuracy: 0.7203 768/3595 [=====>........................] - ETA: 1s - loss: 0.8049 - accuracy: 0.7214 896/3595 [======>.......................] - ETA: 1s - loss: 0.8410 - accuracy: 0.7165 1024/3595 [=======>......................] - ETA: 1s - loss: 0.8470 - accuracy: 0.7119 1152/3595 [========>.....................] - ETA: 1s - loss: 0.8294 - accuracy: 0.7170 1280/3595 [=========>....................] - ETA: 1s - loss: 0.8252 - accuracy: 0.7195 1408/3595 [==========>...................] - ETA: 1s - loss: 0.8267 - accuracy: 0.7202 1504/3595 [===========>..................] - ETA: 1s - loss: 0.8236 - accuracy: 0.7221 1632/3595 [============>.................] - ETA: 0s - loss: 0.8262 - accuracy: 0.7212 1760/3595 [=============>................] - ETA: 0s - loss: 0.8289 - accuracy: 0.7176 1888/3595 [==============>...............] - ETA: 0s - loss: 0.8189 - accuracy: 0.7209 2016/3595 [===============>..............] - ETA: 0s - loss: 0.8240 - accuracy: 0.7212 2144/3595 [================>.............] - ETA: 0s - loss: 0.8186 - accuracy: 0.7239 2272/3595 [=================>............] - ETA: 0s - loss: 0.8163 - accuracy: 0.7223 2400/3595 [===================>..........] - ETA: 0s - loss: 0.8169 - accuracy: 0.7196 2528/3595 [====================>.........] - ETA: 0s - loss: 0.8205 - accuracy: 0.7184 2656/3595 [=====================>........] - ETA: 0s - loss: 0.8234 - accuracy: 0.7176 2784/3595 [======================>.......] - ETA: 0s - loss: 0.8235 - accuracy: 0.7188 2912/3595 [=======================>......] - ETA: 0s - loss: 0.8250 - accuracy: 0.7177 3040/3595 [========================>.....] - ETA: 0s - loss: 0.8302 - accuracy: 0.7151 3168/3595 [=========================>....] - ETA: 0s - loss: 0.8316 - accuracy: 0.7131 3296/3595 [==========================>...] - ETA: 0s - loss: 0.8281 - accuracy: 0.7130 3424/3595 [===========================>..] - ETA: 0s - loss: 0.8281 - accuracy: 0.7106 3552/3595 [============================>.] - ETA: 0s - loss: 0.8263 - accuracy: 0.7111 3595/3595 [==============================] - 2s 527us/sample - loss: 0.8265 - accuracy: 0.7107 - val_loss: 0.9929 - val_accuracy: 0.6363 Epoch 22/28 32/3595 [..............................] - ETA: 1s - loss: 0.8348 - accuracy: 0.7188 160/3595 [>.............................] - ETA: 1s - loss: 0.7880 - accuracy: 0.7000 288/3595 [=>............................] - ETA: 1s - loss: 0.8138 - accuracy: 0.6979 416/3595 [==>...........................] - ETA: 1s - loss: 0.8093 - accuracy: 0.7043 544/3595 [===>..........................] - ETA: 1s - loss: 0.8048 - accuracy: 0.7132 640/3595 [====>.........................] - ETA: 1s - loss: 0.7967 - accuracy: 0.7172 768/3595 [=====>........................] - ETA: 1s - loss: 0.7947 - accuracy: 0.7201 896/3595 [======>.......................] - ETA: 1s - loss: 0.7996 - accuracy: 0.7176 1024/3595 [=======>......................] - ETA: 1s - loss: 0.7992 - accuracy: 0.7168 1152/3595 [========>.....................] - ETA: 1s - loss: 0.7912 - accuracy: 0.7231 1280/3595 [=========>....................] - ETA: 1s - loss: 0.7834 - accuracy: 0.7234 1408/3595 [==========>...................] - ETA: 1s - loss: 0.7793 - accuracy: 0.7259 1536/3595 [===========>..................] - ETA: 1s - loss: 0.7798 - accuracy: 0.7272 1664/3595 [============>.................] - ETA: 0s - loss: 0.7784 - accuracy: 0.7260 1792/3595 [=============>................] - ETA: 0s - loss: 0.7765 - accuracy: 0.7305 1920/3595 [===============>..............] - ETA: 0s - loss: 0.7736 - accuracy: 0.7318 2048/3595 [================>.............] - ETA: 0s - loss: 0.7772 - accuracy: 0.7319 2176/3595 [=================>............] - ETA: 0s - loss: 0.7833 - accuracy: 0.7312 2304/3595 [==================>...........] - ETA: 0s - loss: 0.7725 - accuracy: 0.7339 2432/3595 [===================>..........] - ETA: 0s - loss: 0.7786 - accuracy: 0.7299 2528/3595 [====================>.........] - ETA: 0s - loss: 0.7818 - accuracy: 0.7267 2688/3595 [=====================>........] - ETA: 0s - loss: 0.7859 - accuracy: 0.7247 2816/3595 [======================>.......] - ETA: 0s - loss: 0.7828 - accuracy: 0.7241 2944/3595 [=======================>......] - ETA: 0s - loss: 0.7863 - accuracy: 0.7218 3072/3595 [========================>.....] - ETA: 0s - loss: 0.7855 - accuracy: 0.7220 3200/3595 [=========================>....] - ETA: 0s - loss: 0.7826 - accuracy: 0.7228 3328/3595 [==========================>...] - ETA: 0s - loss: 0.7782 - accuracy: 0.7251 3456/3595 [===========================>..] - ETA: 0s - loss: 0.7816 - accuracy: 0.7237 3584/3595 [============================>.] - ETA: 0s - loss: 0.7861 - accuracy: 0.7213 3595/3595 [==============================] - 2s 522us/sample - loss: 0.7872 - accuracy: 0.7204 - val_loss: 1.0140 - val_accuracy: 0.6307 Epoch 23/28 32/3595 [..............................] - ETA: 1s - loss: 0.9137 - accuracy: 0.7188 160/3595 [>.............................] - ETA: 1s - loss: 0.6864 - accuracy: 0.7812 288/3595 [=>............................] - ETA: 1s - loss: 0.6824 - accuracy: 0.7778 416/3595 [==>...........................] - ETA: 1s - loss: 0.7096 - accuracy: 0.7716 512/3595 [===>..........................] - ETA: 1s - loss: 0.7168 - accuracy: 0.7598 608/3595 [====>.........................] - ETA: 1s - loss: 0.7089 - accuracy: 0.7599 736/3595 [=====>........................] - ETA: 1s - loss: 0.7284 - accuracy: 0.7446 864/3595 [======>.......................] - ETA: 1s - loss: 0.7576 - accuracy: 0.7396 960/3595 [=======>......................] - ETA: 1s - loss: 0.7483 - accuracy: 0.7437 1088/3595 [========>.....................] - ETA: 1s - loss: 0.7352 - accuracy: 0.7518 1216/3595 [=========>....................] - ETA: 1s - loss: 0.7486 - accuracy: 0.7451 1344/3595 [==========>...................] - ETA: 1s - loss: 0.7590 - accuracy: 0.7433 1472/3595 [===========>..................] - ETA: 1s - loss: 0.7663 - accuracy: 0.7330 1600/3595 [============>.................] - ETA: 1s - loss: 0.7754 - accuracy: 0.7306 1728/3595 [=============>................] - ETA: 0s - loss: 0.7763 - accuracy: 0.7303 1856/3595 [==============>...............] - ETA: 0s - loss: 0.7794 - accuracy: 0.7284 1984/3595 [===============>..............] - ETA: 0s - loss: 0.7804 - accuracy: 0.7258 2112/3595 [================>.............] - ETA: 0s - loss: 0.7792 - accuracy: 0.7230 2240/3595 [=================>............] - ETA: 0s - loss: 0.7855 - accuracy: 0.7228 2368/3595 [==================>...........] - ETA: 0s - loss: 0.7814 - accuracy: 0.7221 2496/3595 [===================>..........] - ETA: 0s - loss: 0.7813 - accuracy: 0.7204 2624/3595 [====================>.........] - ETA: 0s - loss: 0.7795 - accuracy: 0.7210 2752/3595 [=====================>........] - ETA: 0s - loss: 0.7740 - accuracy: 0.7231 2880/3595 [=======================>......] - ETA: 0s - loss: 0.7741 - accuracy: 0.7236 3008/3595 [========================>.....] - ETA: 0s - loss: 0.7778 - accuracy: 0.7221 3136/3595 [=========================>....] - ETA: 0s - loss: 0.7777 - accuracy: 0.7226 3264/3595 [==========================>...] - ETA: 0s - loss: 0.7727 - accuracy: 0.7249 3392/3595 [===========================>..] - ETA: 0s - loss: 0.7726 - accuracy: 0.7261 3552/3595 [============================>.] - ETA: 0s - loss: 0.7748 - accuracy: 0.7249 3595/3595 [==============================] - 2s 535us/sample - loss: 0.7741 - accuracy: 0.7252 - val_loss: 0.9919 - val_accuracy: 0.6440 Epoch 24/28 32/3595 [..............................] - ETA: 1s - loss: 0.8341 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 1s - loss: 0.9728 - accuracy: 0.6250 288/3595 [=>............................] - ETA: 1s - loss: 0.7971 - accuracy: 0.7153 416/3595 [==>...........................] - ETA: 1s - loss: 0.7710 - accuracy: 0.7332 512/3595 [===>..........................] - ETA: 1s - loss: 0.7563 - accuracy: 0.7402 640/3595 [====>.........................] - ETA: 1s - loss: 0.7317 - accuracy: 0.7422 768/3595 [=====>........................] - ETA: 1s - loss: 0.7407 - accuracy: 0.7422 896/3595 [======>.......................] - ETA: 1s - loss: 0.7303 - accuracy: 0.7400 1024/3595 [=======>......................] - ETA: 1s - loss: 0.7372 - accuracy: 0.7363 1120/3595 [========>.....................] - ETA: 1s - loss: 0.7422 - accuracy: 0.7402 1248/3595 [=========>....................] - ETA: 1s - loss: 0.7355 - accuracy: 0.7412 1376/3595 [==========>...................] - ETA: 1s - loss: 0.7403 - accuracy: 0.7413 1504/3595 [===========>..................] - ETA: 1s - loss: 0.7374 - accuracy: 0.7427 1632/3595 [============>.................] - ETA: 0s - loss: 0.7362 - accuracy: 0.7451 1760/3595 [=============>................] - ETA: 0s - loss: 0.7392 - accuracy: 0.7420 1888/3595 [==============>...............] - ETA: 0s - loss: 0.7396 - accuracy: 0.7415 2016/3595 [===============>..............] - ETA: 0s - loss: 0.7398 - accuracy: 0.7411 2144/3595 [================>.............] - ETA: 0s - loss: 0.7404 - accuracy: 0.7416 2272/3595 [=================>............] - ETA: 0s - loss: 0.7363 - accuracy: 0.7438 2400/3595 [===================>..........] - ETA: 0s - loss: 0.7329 - accuracy: 0.7429 2528/3595 [====================>.........] - ETA: 0s - loss: 0.7311 - accuracy: 0.7425 2656/3595 [=====================>........] - ETA: 0s - loss: 0.7307 - accuracy: 0.7428 2784/3595 [======================>.......] - ETA: 0s - loss: 0.7305 - accuracy: 0.7407 2912/3595 [=======================>......] - ETA: 0s - loss: 0.7292 - accuracy: 0.7418 3040/3595 [========================>.....] - ETA: 0s - loss: 0.7311 - accuracy: 0.7408 3168/3595 [=========================>....] - ETA: 0s - loss: 0.7364 - accuracy: 0.7374 3296/3595 [==========================>...] - ETA: 0s - loss: 0.7365 - accuracy: 0.7397 3424/3595 [===========================>..] - ETA: 0s - loss: 0.7374 - accuracy: 0.7401 3552/3595 [============================>.] - ETA: 0s - loss: 0.7338 - accuracy: 0.7435 3595/3595 [==============================] - 2s 535us/sample - loss: 0.7367 - accuracy: 0.7413 - val_loss: 0.9661 - val_accuracy: 0.6352 Epoch 25/28 32/3595 [..............................] - ETA: 1s - loss: 0.6900 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 1s - loss: 0.6604 - accuracy: 0.7625 256/3595 [=>............................] - ETA: 1s - loss: 0.6635 - accuracy: 0.7734 384/3595 [==>...........................] - ETA: 1s - loss: 0.7092 - accuracy: 0.7604 512/3595 [===>..........................] - ETA: 1s - loss: 0.6976 - accuracy: 0.7656 640/3595 [====>.........................] - ETA: 1s - loss: 0.7004 - accuracy: 0.7609 768/3595 [=====>........................] - ETA: 1s - loss: 0.7022 - accuracy: 0.7552 864/3595 [======>.......................] - ETA: 1s - loss: 0.7081 - accuracy: 0.7546 992/3595 [=======>......................] - ETA: 1s - loss: 0.7252 - accuracy: 0.7460 1120/3595 [========>.....................] - ETA: 1s - loss: 0.7145 - accuracy: 0.7509 1248/3595 [=========>....................] - ETA: 1s - loss: 0.7272 - accuracy: 0.7468 1376/3595 [==========>...................] - ETA: 1s - loss: 0.7403 - accuracy: 0.7442 1504/3595 [===========>..................] - ETA: 1s - loss: 0.7403 - accuracy: 0.7453 1664/3595 [============>.................] - ETA: 0s - loss: 0.7301 - accuracy: 0.7494 1824/3595 [==============>...............] - ETA: 0s - loss: 0.7128 - accuracy: 0.7560 1920/3595 [===============>..............] - ETA: 0s - loss: 0.7130 - accuracy: 0.7573 2080/3595 [================>.............] - ETA: 0s - loss: 0.7180 - accuracy: 0.7558 2176/3595 [=================>............] - ETA: 0s - loss: 0.7151 - accuracy: 0.7555 2304/3595 [==================>...........] - ETA: 0s - loss: 0.7207 - accuracy: 0.7522 2432/3595 [===================>..........] - ETA: 0s - loss: 0.7203 - accuracy: 0.7537 2560/3595 [====================>.........] - ETA: 0s - loss: 0.7165 - accuracy: 0.7566 2688/3595 [=====================>........] - ETA: 0s - loss: 0.7148 - accuracy: 0.7589 2816/3595 [======================>.......] - ETA: 0s - loss: 0.7162 - accuracy: 0.7578 2944/3595 [=======================>......] - ETA: 0s - loss: 0.7132 - accuracy: 0.7561 3104/3595 [========================>.....] - ETA: 0s - loss: 0.7079 - accuracy: 0.7577 3232/3595 [=========================>....] - ETA: 0s - loss: 0.7061 - accuracy: 0.7602 3360/3595 [===========================>..] - ETA: 0s - loss: 0.7053 - accuracy: 0.7604 3456/3595 [===========================>..] - ETA: 0s - loss: 0.7040 - accuracy: 0.7604 3584/3595 [============================>.] - ETA: 0s - loss: 0.7058 - accuracy: 0.7586 3595/3595 [==============================] - 2s 531us/sample - loss: 0.7071 - accuracy: 0.7577 - val_loss: 0.9531 - val_accuracy: 0.6552 Epoch 26/28 32/3595 [..............................] - ETA: 3s - loss: 0.8912 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 2s - loss: 0.7104 - accuracy: 0.7500 288/3595 [=>............................] - ETA: 1s - loss: 0.6820 - accuracy: 0.7778 384/3595 [==>...........................] - ETA: 1s - loss: 0.7135 - accuracy: 0.7552 512/3595 [===>..........................] - ETA: 1s - loss: 0.7229 - accuracy: 0.7480 640/3595 [====>.........................] - ETA: 1s - loss: 0.7026 - accuracy: 0.7531 768/3595 [=====>........................] - ETA: 1s - loss: 0.6973 - accuracy: 0.7617 896/3595 [======>.......................] - ETA: 1s - loss: 0.6943 - accuracy: 0.7634 1024/3595 [=======>......................] - ETA: 1s - loss: 0.6989 - accuracy: 0.7578 1152/3595 [========>.....................] - ETA: 1s - loss: 0.6894 - accuracy: 0.7622 1280/3595 [=========>....................] - ETA: 1s - loss: 0.6824 - accuracy: 0.7688 1408/3595 [==========>...................] - ETA: 1s - loss: 0.7021 - accuracy: 0.7656 1536/3595 [===========>..................] - ETA: 1s - loss: 0.7098 - accuracy: 0.7624 1664/3595 [============>.................] - ETA: 0s - loss: 0.7017 - accuracy: 0.7632 1792/3595 [=============>................] - ETA: 0s - loss: 0.7014 - accuracy: 0.7640 1920/3595 [===============>..............] - ETA: 0s - loss: 0.7016 - accuracy: 0.7609 2048/3595 [================>.............] - ETA: 0s - loss: 0.7099 - accuracy: 0.7534 2176/3595 [=================>............] - ETA: 0s - loss: 0.7182 - accuracy: 0.7523 2304/3595 [==================>...........] - ETA: 0s - loss: 0.7284 - accuracy: 0.7478 2464/3595 [===================>..........] - ETA: 0s - loss: 0.7286 - accuracy: 0.7459 2624/3595 [====================>.........] - ETA: 0s - loss: 0.7297 - accuracy: 0.7458 2752/3595 [=====================>........] - ETA: 0s - loss: 0.7260 - accuracy: 0.7475 2880/3595 [=======================>......] - ETA: 0s - loss: 0.7265 - accuracy: 0.7462 3008/3595 [========================>.....] - ETA: 0s - loss: 0.7271 - accuracy: 0.7453 3136/3595 [=========================>....] - ETA: 0s - loss: 0.7192 - accuracy: 0.7494 3264/3595 [==========================>...] - ETA: 0s - loss: 0.7144 - accuracy: 0.7518 3392/3595 [===========================>..] - ETA: 0s - loss: 0.7157 - accuracy: 0.7512 3520/3595 [============================>.] - ETA: 0s - loss: 0.7088 - accuracy: 0.7540 3595/3595 [==============================] - 2s 522us/sample - loss: 0.7112 - accuracy: 0.7522 - val_loss: 0.9949 - val_accuracy: 0.6274 Epoch 27/28 32/3595 [..............................] - ETA: 1s - loss: 0.6788 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 1s - loss: 0.6429 - accuracy: 0.7625 288/3595 [=>............................] - ETA: 1s - loss: 0.6253 - accuracy: 0.7812 384/3595 [==>...........................] - ETA: 1s - loss: 0.6292 - accuracy: 0.7812 512/3595 [===>..........................] - ETA: 1s - loss: 0.6247 - accuracy: 0.7793 640/3595 [====>.........................] - ETA: 1s - loss: 0.6283 - accuracy: 0.7703 768/3595 [=====>........................] - ETA: 1s - loss: 0.6352 - accuracy: 0.7669 896/3595 [======>.......................] - ETA: 1s - loss: 0.6658 - accuracy: 0.7600 1024/3595 [=======>......................] - ETA: 1s - loss: 0.6670 - accuracy: 0.7607 1152/3595 [========>.....................] - ETA: 1s - loss: 0.6713 - accuracy: 0.7578 1280/3595 [=========>....................] - ETA: 1s - loss: 0.6714 - accuracy: 0.7586 1408/3595 [==========>...................] - ETA: 1s - loss: 0.6703 - accuracy: 0.7635 1536/3595 [===========>..................] - ETA: 1s - loss: 0.6784 - accuracy: 0.7598 1664/3595 [============>.................] - ETA: 0s - loss: 0.6708 - accuracy: 0.7632 1792/3595 [=============>................] - ETA: 0s - loss: 0.6652 - accuracy: 0.7679 1920/3595 [===============>..............] - ETA: 0s - loss: 0.6820 - accuracy: 0.7609 2016/3595 [===============>..............] - ETA: 0s - loss: 0.6809 - accuracy: 0.7599 2144/3595 [================>.............] - ETA: 0s - loss: 0.6816 - accuracy: 0.7598 2272/3595 [=================>............] - ETA: 0s - loss: 0.6791 - accuracy: 0.7588 2400/3595 [===================>..........] - ETA: 0s - loss: 0.6753 - accuracy: 0.7608 2528/3595 [====================>.........] - ETA: 0s - loss: 0.6813 - accuracy: 0.7615 2656/3595 [=====================>........] - ETA: 0s - loss: 0.6769 - accuracy: 0.7639 2784/3595 [======================>.......] - ETA: 0s - loss: 0.6823 - accuracy: 0.7629 2912/3595 [=======================>......] - ETA: 0s - loss: 0.6838 - accuracy: 0.7617 3040/3595 [========================>.....] - ETA: 0s - loss: 0.6784 - accuracy: 0.7641 3168/3595 [=========================>....] - ETA: 0s - loss: 0.6834 - accuracy: 0.7617 3296/3595 [==========================>...] - ETA: 0s - loss: 0.6810 - accuracy: 0.7633 3424/3595 [===========================>..] - ETA: 0s - loss: 0.6792 - accuracy: 0.7637 3520/3595 [============================>.] - ETA: 0s - loss: 0.6785 - accuracy: 0.7642 3595/3595 [==============================] - 2s 531us/sample - loss: 0.6803 - accuracy: 0.7647 - val_loss: 0.9663 - val_accuracy: 0.6485 Epoch 28/28 32/3595 [..............................] - ETA: 1s - loss: 0.7868 - accuracy: 0.8125 160/3595 [>.............................] - ETA: 1s - loss: 0.6892 - accuracy: 0.7812 288/3595 [=>............................] - ETA: 1s - loss: 0.6375 - accuracy: 0.7847 416/3595 [==>...........................] - ETA: 1s - loss: 0.6593 - accuracy: 0.7692 544/3595 [===>..........................] - ETA: 1s - loss: 0.6625 - accuracy: 0.7739 672/3595 [====>.........................] - ETA: 1s - loss: 0.6575 - accuracy: 0.7827 800/3595 [=====>........................] - ETA: 1s - loss: 0.6574 - accuracy: 0.7825 928/3595 [======>.......................] - ETA: 1s - loss: 0.6499 - accuracy: 0.7877 1056/3595 [=======>......................] - ETA: 1s - loss: 0.6515 - accuracy: 0.7888 1184/3595 [========>.....................] - ETA: 1s - loss: 0.6524 - accuracy: 0.7880 1312/3595 [=========>....................] - ETA: 1s - loss: 0.6539 - accuracy: 0.7866 1408/3595 [==========>...................] - ETA: 1s - loss: 0.6507 - accuracy: 0.7884 1536/3595 [===========>..................] - ETA: 1s - loss: 0.6552 - accuracy: 0.7871 1664/3595 [============>.................] - ETA: 0s - loss: 0.6627 - accuracy: 0.7867 1792/3595 [=============>................] - ETA: 0s - loss: 0.6770 - accuracy: 0.7768 1920/3595 [===============>..............] - ETA: 0s - loss: 0.6736 - accuracy: 0.7786 2048/3595 [================>.............] - ETA: 0s - loss: 0.6688 - accuracy: 0.7803 2176/3595 [=================>............] - ETA: 0s - loss: 0.6639 - accuracy: 0.7794 2272/3595 [=================>............] - ETA: 0s - loss: 0.6677 - accuracy: 0.7760 2400/3595 [===================>..........] - ETA: 0s - loss: 0.6676 - accuracy: 0.7742 2528/3595 [====================>.........] - ETA: 0s - loss: 0.6642 - accuracy: 0.7753 2656/3595 [=====================>........] - ETA: 0s - loss: 0.6701 - accuracy: 0.7730 2752/3595 [=====================>........] - ETA: 0s - loss: 0.6686 - accuracy: 0.7740 2880/3595 [=======================>......] - ETA: 0s - loss: 0.6695 - accuracy: 0.7747 2976/3595 [=======================>......] - ETA: 0s - loss: 0.6719 - accuracy: 0.7735 3072/3595 [========================>.....] - ETA: 0s - loss: 0.6741 - accuracy: 0.7715 3168/3595 [=========================>....] - ETA: 0s - loss: 0.6712 - accuracy: 0.7724 3296/3595 [==========================>...] - ETA: 0s - loss: 0.6719 - accuracy: 0.7728 3424/3595 [===========================>..] - ETA: 0s - loss: 0.6738 - accuracy: 0.7722 3552/3595 [============================>.] - ETA: 0s - loss: 0.6725 - accuracy: 0.7722 3595/3595 [==============================] - 2s 549us/sample - loss: 0.6737 - accuracy: 0.7711 - val_loss: 0.9783 - val_accuracy: 0.6507 Evaluating model for iteration 0... 1498/1498 - 0s - loss: 0.9543 - accuracy: 0.6602 Accuracy for iteration 0 0.6602135896682739 Training model for iteration 1... Train on 3595 samples, validate on 899 samples Epoch 1/28 32/3595 [..............................] - ETA: 41s - loss: 3.6598 - accuracy: 0.1250 160/3595 [>.............................] - ETA: 9s - loss: 3.3394 - accuracy: 0.0875 288/3595 [=>............................] - ETA: 5s - loss: 3.2255 - accuracy: 0.0903 416/3595 [==>...........................] - ETA: 4s - loss: 3.2471 - accuracy: 0.0986 576/3595 [===>..........................] - ETA: 3s - loss: 3.2469 - accuracy: 0.0903 704/3595 [====>.........................] - ETA: 2s - loss: 3.2030 - accuracy: 0.0952 832/3595 [=====>........................] - ETA: 2s - loss: 3.1505 - accuracy: 0.1082 960/3595 [=======>......................] - ETA: 2s - loss: 3.1152 - accuracy: 0.1177 1088/3595 [========>.....................] - ETA: 2s - loss: 3.0771 - accuracy: 0.1186 1216/3595 [=========>....................] - ETA: 1s - loss: 3.0464 - accuracy: 0.1209 1344/3595 [==========>...................] - ETA: 1s - loss: 3.0016 - accuracy: 0.1257 1472/3595 [===========>..................] - ETA: 1s - loss: 2.9869 - accuracy: 0.1284 1600/3595 [============>.................] - ETA: 1s - loss: 2.9569 - accuracy: 0.1312 1760/3595 [=============>................] - ETA: 1s - loss: 2.9416 - accuracy: 0.1335 1888/3595 [==============>...............] - ETA: 1s - loss: 2.9200 - accuracy: 0.1351 2016/3595 [===============>..............] - ETA: 1s - loss: 2.9025 - accuracy: 0.1414 2144/3595 [================>.............] - ETA: 0s - loss: 2.8926 - accuracy: 0.1418 2240/3595 [=================>............] - ETA: 0s - loss: 2.8793 - accuracy: 0.1442 2368/3595 [==================>...........] - ETA: 0s - loss: 2.8478 - accuracy: 0.1512 2464/3595 [===================>..........] - ETA: 0s - loss: 2.8275 - accuracy: 0.1550 2560/3595 [====================>.........] - ETA: 0s - loss: 2.8202 - accuracy: 0.1586 2688/3595 [=====================>........] - ETA: 0s - loss: 2.8080 - accuracy: 0.1581 2816/3595 [======================>.......] - ETA: 0s - loss: 2.7958 - accuracy: 0.1605 2944/3595 [=======================>......] - ETA: 0s - loss: 2.7846 - accuracy: 0.1603 3072/3595 [========================>.....] - ETA: 0s - loss: 2.7697 - accuracy: 0.1644 3200/3595 [=========================>....] - ETA: 0s - loss: 2.7582 - accuracy: 0.1684 3328/3595 [==========================>...] - ETA: 0s - loss: 2.7363 - accuracy: 0.1734 3456/3595 [===========================>..] - ETA: 0s - loss: 2.7165 - accuracy: 0.1756 3584/3595 [============================>.] - ETA: 0s - loss: 2.7016 - accuracy: 0.1802 3595/3595 [==============================] - 2s 693us/sample - loss: 2.6991 - accuracy: 0.1808 - val_loss: 2.0670 - val_accuracy: 0.2848 Epoch 2/28 32/3595 [..............................] - ETA: 1s - loss: 2.3790 - accuracy: 0.2812 160/3595 [>.............................] - ETA: 1s - loss: 2.2605 - accuracy: 0.2875 256/3595 [=>............................] - ETA: 1s - loss: 2.2531 - accuracy: 0.2969 384/3595 [==>...........................] - ETA: 1s - loss: 2.2473 - accuracy: 0.2812 512/3595 [===>..........................] - ETA: 1s - loss: 2.2189 - accuracy: 0.2891 640/3595 [====>.........................] - ETA: 1s - loss: 2.1786 - accuracy: 0.2953 736/3595 [=====>........................] - ETA: 1s - loss: 2.1761 - accuracy: 0.3003 864/3595 [======>.......................] - ETA: 1s - loss: 2.1814 - accuracy: 0.2986 992/3595 [=======>......................] - ETA: 1s - loss: 2.2062 - accuracy: 0.2944 1120/3595 [========>.....................] - ETA: 1s - loss: 2.2161 - accuracy: 0.2848 1248/3595 [=========>....................] - ETA: 1s - loss: 2.2267 - accuracy: 0.2837 1376/3595 [==========>...................] - ETA: 1s - loss: 2.2114 - accuracy: 0.2805 1504/3595 [===========>..................] - ETA: 1s - loss: 2.2069 - accuracy: 0.2832 1600/3595 [============>.................] - ETA: 1s - loss: 2.1970 - accuracy: 0.2856 1728/3595 [=============>................] - ETA: 0s - loss: 2.1895 - accuracy: 0.2841 1856/3595 [==============>...............] - ETA: 0s - loss: 2.1820 - accuracy: 0.2888 1952/3595 [===============>..............] - ETA: 0s - loss: 2.1700 - accuracy: 0.2920 2080/3595 [================>.............] - ETA: 0s - loss: 2.1636 - accuracy: 0.2913 2208/3595 [=================>............] - ETA: 0s - loss: 2.1522 - accuracy: 0.2971 2304/3595 [==================>...........] - ETA: 0s - loss: 2.1454 - accuracy: 0.2999 2432/3595 [===================>..........] - ETA: 0s - loss: 2.1433 - accuracy: 0.2998 2560/3595 [====================>.........] - ETA: 0s - loss: 2.1367 - accuracy: 0.2992 2688/3595 [=====================>........] - ETA: 0s - loss: 2.1312 - accuracy: 0.3032 2816/3595 [======================>.......] - ETA: 0s - loss: 2.1224 - accuracy: 0.3040 2944/3595 [=======================>......] - ETA: 0s - loss: 2.1192 - accuracy: 0.3071 3072/3595 [========================>.....] - ETA: 0s - loss: 2.1145 - accuracy: 0.3083 3200/3595 [=========================>....] - ETA: 0s - loss: 2.1117 - accuracy: 0.3100 3296/3595 [==========================>...] - ETA: 0s - loss: 2.1045 - accuracy: 0.3122 3424/3595 [===========================>..] - ETA: 0s - loss: 2.0978 - accuracy: 0.3116 3552/3595 [============================>.] - ETA: 0s - loss: 2.0905 - accuracy: 0.3133 3595/3595 [==============================] - 2s 556us/sample - loss: 2.0887 - accuracy: 0.3143 - val_loss: 1.7145 - val_accuracy: 0.3849 Epoch 3/28 32/3595 [..............................] - ETA: 1s - loss: 1.9549 - accuracy: 0.3125 128/3595 [>.............................] - ETA: 2s - loss: 1.9104 - accuracy: 0.3281 256/3595 [=>............................] - ETA: 1s - loss: 1.9206 - accuracy: 0.3398 384/3595 [==>...........................] - ETA: 1s - loss: 1.9114 - accuracy: 0.3516 512/3595 [===>..........................] - ETA: 1s - loss: 1.8363 - accuracy: 0.3770 640/3595 [====>.........................] - ETA: 1s - loss: 1.8783 - accuracy: 0.3688 736/3595 [=====>........................] - ETA: 1s - loss: 1.8430 - accuracy: 0.3791 832/3595 [=====>........................] - ETA: 1s - loss: 1.8506 - accuracy: 0.3798 928/3595 [======>.......................] - ETA: 1s - loss: 1.8733 - accuracy: 0.3772 1024/3595 [=======>......................] - ETA: 1s - loss: 1.8641 - accuracy: 0.3730 1120/3595 [========>.....................] - ETA: 1s - loss: 1.8533 - accuracy: 0.3732 1248/3595 [=========>....................] - ETA: 1s - loss: 1.8409 - accuracy: 0.3798 1376/3595 [==========>...................] - ETA: 1s - loss: 1.8341 - accuracy: 0.3837 1504/3595 [===========>..................] - ETA: 1s - loss: 1.8309 - accuracy: 0.3836 1600/3595 [============>.................] - ETA: 1s - loss: 1.8253 - accuracy: 0.3819 1728/3595 [=============>................] - ETA: 1s - loss: 1.8353 - accuracy: 0.3767 1856/3595 [==============>...............] - ETA: 0s - loss: 1.8364 - accuracy: 0.3728 1984/3595 [===============>..............] - ETA: 0s - loss: 1.8155 - accuracy: 0.3780 2112/3595 [================>.............] - ETA: 0s - loss: 1.8171 - accuracy: 0.3759 2240/3595 [=================>............] - ETA: 0s - loss: 1.8151 - accuracy: 0.3768 2368/3595 [==================>...........] - ETA: 0s - loss: 1.8117 - accuracy: 0.3767 2496/3595 [===================>..........] - ETA: 0s - loss: 1.8132 - accuracy: 0.3758 2624/3595 [====================>.........] - ETA: 0s - loss: 1.7957 - accuracy: 0.3815 2752/3595 [=====================>........] - ETA: 0s - loss: 1.7981 - accuracy: 0.3805 2880/3595 [=======================>......] - ETA: 0s - loss: 1.7918 - accuracy: 0.3812 3008/3595 [========================>.....] - ETA: 0s - loss: 1.7889 - accuracy: 0.3833 3136/3595 [=========================>....] - ETA: 0s - loss: 1.7766 - accuracy: 0.3890 3264/3595 [==========================>...] - ETA: 0s - loss: 1.7754 - accuracy: 0.3879 3360/3595 [===========================>..] - ETA: 0s - loss: 1.7708 - accuracy: 0.3884 3488/3595 [============================>.] - ETA: 0s - loss: 1.7634 - accuracy: 0.3913 3595/3595 [==============================] - 2s 561us/sample - loss: 1.7567 - accuracy: 0.3933 - val_loss: 1.5509 - val_accuracy: 0.4394 Epoch 4/28 32/3595 [..............................] - ETA: 3s - loss: 1.6635 - accuracy: 0.4375 160/3595 [>.............................] - ETA: 2s - loss: 1.5728 - accuracy: 0.4437 288/3595 [=>............................] - ETA: 1s - loss: 1.6420 - accuracy: 0.4306 384/3595 [==>...........................] - ETA: 1s - loss: 1.6487 - accuracy: 0.4271 512/3595 [===>..........................] - ETA: 1s - loss: 1.6525 - accuracy: 0.4355 640/3595 [====>.........................] - ETA: 1s - loss: 1.6850 - accuracy: 0.4313 768/3595 [=====>........................] - ETA: 1s - loss: 1.6646 - accuracy: 0.4323 896/3595 [======>.......................] - ETA: 1s - loss: 1.6621 - accuracy: 0.4275 1024/3595 [=======>......................] - ETA: 1s - loss: 1.6601 - accuracy: 0.4258 1152/3595 [========>.....................] - ETA: 1s - loss: 1.6425 - accuracy: 0.4366 1280/3595 [=========>....................] - ETA: 1s - loss: 1.6529 - accuracy: 0.4359 1408/3595 [==========>...................] - ETA: 1s - loss: 1.6653 - accuracy: 0.4297 1536/3595 [===========>..................] - ETA: 1s - loss: 1.6586 - accuracy: 0.4297 1632/3595 [============>.................] - ETA: 1s - loss: 1.6616 - accuracy: 0.4289 1760/3595 [=============>................] - ETA: 0s - loss: 1.6439 - accuracy: 0.4307 1888/3595 [==============>...............] - ETA: 0s - loss: 1.6322 - accuracy: 0.4349 2016/3595 [===============>..............] - ETA: 0s - loss: 1.6336 - accuracy: 0.4375 2144/3595 [================>.............] - ETA: 0s - loss: 1.6438 - accuracy: 0.4347 2272/3595 [=================>............] - ETA: 0s - loss: 1.6496 - accuracy: 0.4322 2400/3595 [===================>..........] - ETA: 0s - loss: 1.6454 - accuracy: 0.4317 2528/3595 [====================>.........] - ETA: 0s - loss: 1.6445 - accuracy: 0.4320 2624/3595 [====================>.........] - ETA: 0s - loss: 1.6426 - accuracy: 0.4333 2752/3595 [=====================>........] - ETA: 0s - loss: 1.6389 - accuracy: 0.4350 2880/3595 [=======================>......] - ETA: 0s - loss: 1.6316 - accuracy: 0.4358 3008/3595 [========================>.....] - ETA: 0s - loss: 1.6325 - accuracy: 0.4362 3136/3595 [=========================>....] - ETA: 0s - loss: 1.6269 - accuracy: 0.4369 3232/3595 [=========================>....] - ETA: 0s - loss: 1.6225 - accuracy: 0.4390 3360/3595 [===========================>..] - ETA: 0s - loss: 1.6209 - accuracy: 0.4417 3488/3595 [============================>.] - ETA: 0s - loss: 1.6164 - accuracy: 0.4429 3595/3595 [==============================] - 2s 543us/sample - loss: 1.6153 - accuracy: 0.4406 - val_loss: 1.4370 - val_accuracy: 0.4783 Epoch 5/28 32/3595 [..............................] - ETA: 1s - loss: 1.5991 - accuracy: 0.5312 160/3595 [>.............................] - ETA: 1s - loss: 1.3986 - accuracy: 0.5063 288/3595 [=>............................] - ETA: 1s - loss: 1.4630 - accuracy: 0.5035 384/3595 [==>...........................] - ETA: 1s - loss: 1.4576 - accuracy: 0.4974 512/3595 [===>..........................] - ETA: 1s - loss: 1.4531 - accuracy: 0.5020 640/3595 [====>.........................] - ETA: 1s - loss: 1.4557 - accuracy: 0.4938 768/3595 [=====>........................] - ETA: 1s - loss: 1.4745 - accuracy: 0.4883 896/3595 [======>.......................] - ETA: 1s - loss: 1.5238 - accuracy: 0.4743 1024/3595 [=======>......................] - ETA: 1s - loss: 1.5301 - accuracy: 0.4678 1152/3595 [========>.....................] - ETA: 1s - loss: 1.5130 - accuracy: 0.4731 1280/3595 [=========>....................] - ETA: 1s - loss: 1.5195 - accuracy: 0.4688 1408/3595 [==========>...................] - ETA: 1s - loss: 1.5170 - accuracy: 0.4723 1536/3595 [===========>..................] - ETA: 1s - loss: 1.5046 - accuracy: 0.4753 1664/3595 [============>.................] - ETA: 0s - loss: 1.5008 - accuracy: 0.4784 1760/3595 [=============>................] - ETA: 0s - loss: 1.4880 - accuracy: 0.4852 1888/3595 [==============>...............] - ETA: 0s - loss: 1.4759 - accuracy: 0.4899 2016/3595 [===============>..............] - ETA: 0s - loss: 1.4826 - accuracy: 0.4861 2144/3595 [================>.............] - ETA: 0s - loss: 1.4879 - accuracy: 0.4837 2272/3595 [=================>............] - ETA: 0s - loss: 1.4852 - accuracy: 0.4846 2368/3595 [==================>...........] - ETA: 0s - loss: 1.4821 - accuracy: 0.4886 2496/3595 [===================>..........] - ETA: 0s - loss: 1.4840 - accuracy: 0.4876 2624/3595 [====================>.........] - ETA: 0s - loss: 1.4820 - accuracy: 0.4886 2752/3595 [=====================>........] - ETA: 0s - loss: 1.4675 - accuracy: 0.4931 2880/3595 [=======================>......] - ETA: 0s - loss: 1.4676 - accuracy: 0.4927 2976/3595 [=======================>......] - ETA: 0s - loss: 1.4654 - accuracy: 0.4909 3104/3595 [========================>.....] - ETA: 0s - loss: 1.4653 - accuracy: 0.4897 3232/3595 [=========================>....] - ETA: 0s - loss: 1.4642 - accuracy: 0.4901 3328/3595 [==========================>...] - ETA: 0s - loss: 1.4687 - accuracy: 0.4886 3456/3595 [===========================>..] - ETA: 0s - loss: 1.4702 - accuracy: 0.4881 3584/3595 [============================>.] - ETA: 0s - loss: 1.4682 - accuracy: 0.4897 3595/3595 [==============================] - 2s 561us/sample - loss: 1.4698 - accuracy: 0.4896 - val_loss: 1.3848 - val_accuracy: 0.4961 Epoch 6/28 32/3595 [..............................] - ETA: 1s - loss: 1.3120 - accuracy: 0.5938 160/3595 [>.............................] - ETA: 1s - loss: 1.4660 - accuracy: 0.4812 288/3595 [=>............................] - ETA: 1s - loss: 1.4577 - accuracy: 0.4826 416/3595 [==>...........................] - ETA: 1s - loss: 1.4074 - accuracy: 0.4952 544/3595 [===>..........................] - ETA: 1s - loss: 1.4182 - accuracy: 0.4926 640/3595 [====>.........................] - ETA: 1s - loss: 1.3934 - accuracy: 0.4953 768/3595 [=====>........................] - ETA: 1s - loss: 1.3826 - accuracy: 0.5026 896/3595 [======>.......................] - ETA: 1s - loss: 1.4074 - accuracy: 0.4944 1024/3595 [=======>......................] - ETA: 1s - loss: 1.4061 - accuracy: 0.4902 1152/3595 [========>.....................] - ETA: 1s - loss: 1.3935 - accuracy: 0.4965 1280/3595 [=========>....................] - ETA: 1s - loss: 1.3897 - accuracy: 0.4961 1408/3595 [==========>...................] - ETA: 1s - loss: 1.3962 - accuracy: 0.4950 1536/3595 [===========>..................] - ETA: 1s - loss: 1.4089 - accuracy: 0.4896 1664/3595 [============>.................] - ETA: 0s - loss: 1.4180 - accuracy: 0.4868 1792/3595 [=============>................] - ETA: 0s - loss: 1.4237 - accuracy: 0.4872 1920/3595 [===============>..............] - ETA: 0s - loss: 1.4234 - accuracy: 0.4891 2048/3595 [================>.............] - ETA: 0s - loss: 1.4183 - accuracy: 0.4912 2176/3595 [=================>............] - ETA: 0s - loss: 1.4172 - accuracy: 0.4903 2272/3595 [=================>............] - ETA: 0s - loss: 1.4164 - accuracy: 0.4925 2400/3595 [===================>..........] - ETA: 0s - loss: 1.4124 - accuracy: 0.4946 2528/3595 [====================>.........] - ETA: 0s - loss: 1.4095 - accuracy: 0.4953 2656/3595 [=====================>........] - ETA: 0s - loss: 1.4071 - accuracy: 0.4977 2784/3595 [======================>.......] - ETA: 0s - loss: 1.4069 - accuracy: 0.4993 2912/3595 [=======================>......] - ETA: 0s - loss: 1.4086 - accuracy: 0.5000 3040/3595 [========================>.....] - ETA: 0s - loss: 1.4017 - accuracy: 0.5033 3136/3595 [=========================>....] - ETA: 0s - loss: 1.4005 - accuracy: 0.5041 3264/3595 [==========================>...] - ETA: 0s - loss: 1.4010 - accuracy: 0.5052 3392/3595 [===========================>..] - ETA: 0s - loss: 1.4010 - accuracy: 0.5044 3520/3595 [============================>.] - ETA: 0s - loss: 1.3954 - accuracy: 0.5051 3595/3595 [==============================] - 2s 535us/sample - loss: 1.3896 - accuracy: 0.5071 - val_loss: 1.2899 - val_accuracy: 0.5428 Epoch 7/28 32/3595 [..............................] - ETA: 1s - loss: 1.3283 - accuracy: 0.5000 160/3595 [>.............................] - ETA: 1s - loss: 1.3102 - accuracy: 0.5375 288/3595 [=>............................] - ETA: 1s - loss: 1.3801 - accuracy: 0.5000 416/3595 [==>...........................] - ETA: 1s - loss: 1.3519 - accuracy: 0.5048 512/3595 [===>..........................] - ETA: 1s - loss: 1.3497 - accuracy: 0.5156 608/3595 [====>.........................] - ETA: 1s - loss: 1.3339 - accuracy: 0.5247 736/3595 [=====>........................] - ETA: 1s - loss: 1.3205 - accuracy: 0.5231 864/3595 [======>.......................] - ETA: 1s - loss: 1.3100 - accuracy: 0.5289 960/3595 [=======>......................] - ETA: 1s - loss: 1.3225 - accuracy: 0.5240 1056/3595 [=======>......................] - ETA: 1s - loss: 1.3541 - accuracy: 0.5133 1152/3595 [========>.....................] - ETA: 1s - loss: 1.3701 - accuracy: 0.5130 1280/3595 [=========>....................] - ETA: 1s - loss: 1.3613 - accuracy: 0.5164 1408/3595 [==========>...................] - ETA: 1s - loss: 1.3511 - accuracy: 0.5199 1504/3595 [===========>..................] - ETA: 1s - loss: 1.3504 - accuracy: 0.5219 1632/3595 [============>.................] - ETA: 1s - loss: 1.3447 - accuracy: 0.5208 1760/3595 [=============>................] - ETA: 0s - loss: 1.3455 - accuracy: 0.5222 1888/3595 [==============>...............] - ETA: 0s - loss: 1.3406 - accuracy: 0.5275 2016/3595 [===============>..............] - ETA: 0s - loss: 1.3345 - accuracy: 0.5263 2144/3595 [================>.............] - ETA: 0s - loss: 1.3198 - accuracy: 0.5345 2240/3595 [=================>............] - ETA: 0s - loss: 1.3143 - accuracy: 0.5353 2368/3595 [==================>...........] - ETA: 0s - loss: 1.3173 - accuracy: 0.5346 2496/3595 [===================>..........] - ETA: 0s - loss: 1.3115 - accuracy: 0.5353 2624/3595 [====================>.........] - ETA: 0s - loss: 1.3084 - accuracy: 0.5354 2752/3595 [=====================>........] - ETA: 0s - loss: 1.3110 - accuracy: 0.5342 2880/3595 [=======================>......] - ETA: 0s - loss: 1.3074 - accuracy: 0.5358 2976/3595 [=======================>......] - ETA: 0s - loss: 1.3077 - accuracy: 0.5356 3104/3595 [========================>.....] - ETA: 0s - loss: 1.3118 - accuracy: 0.5361 3232/3595 [=========================>....] - ETA: 0s - loss: 1.3078 - accuracy: 0.5350 3360/3595 [===========================>..] - ETA: 0s - loss: 1.3098 - accuracy: 0.5324 3488/3595 [============================>.] - ETA: 0s - loss: 1.3112 - accuracy: 0.5321 3595/3595 [==============================] - 2s 550us/sample - loss: 1.3111 - accuracy: 0.5321 - val_loss: 1.2622 - val_accuracy: 0.5328 Epoch 8/28 32/3595 [..............................] - ETA: 1s - loss: 1.0817 - accuracy: 0.5625 160/3595 [>.............................] - ETA: 1s - loss: 1.3246 - accuracy: 0.5125 256/3595 [=>............................] - ETA: 1s - loss: 1.2438 - accuracy: 0.5469 384/3595 [==>...........................] - ETA: 1s - loss: 1.2861 - accuracy: 0.5417 480/3595 [===>..........................] - ETA: 1s - loss: 1.2724 - accuracy: 0.5521 608/3595 [====>.........................] - ETA: 1s - loss: 1.2807 - accuracy: 0.5559 736/3595 [=====>........................] - ETA: 1s - loss: 1.2999 - accuracy: 0.5489 864/3595 [======>.......................] - ETA: 1s - loss: 1.2966 - accuracy: 0.5509 992/3595 [=======>......................] - ETA: 1s - loss: 1.2822 - accuracy: 0.5534 1088/3595 [========>.....................] - ETA: 1s - loss: 1.2804 - accuracy: 0.5515 1184/3595 [========>.....................] - ETA: 1s - loss: 1.2638 - accuracy: 0.5600 1312/3595 [=========>....................] - ETA: 1s - loss: 1.2578 - accuracy: 0.5617 1440/3595 [===========>..................] - ETA: 1s - loss: 1.2586 - accuracy: 0.5604 1568/3595 [============>.................] - ETA: 1s - loss: 1.2593 - accuracy: 0.5587 1696/3595 [=============>................] - ETA: 0s - loss: 1.2548 - accuracy: 0.5619 1792/3595 [=============>................] - ETA: 0s - loss: 1.2592 - accuracy: 0.5619 1920/3595 [===============>..............] - ETA: 0s - loss: 1.2607 - accuracy: 0.5604 2048/3595 [================>.............] - ETA: 0s - loss: 1.2644 - accuracy: 0.5591 2144/3595 [================>.............] - ETA: 0s - loss: 1.2606 - accuracy: 0.5592 2240/3595 [=================>............] - ETA: 0s - loss: 1.2674 - accuracy: 0.5562 2368/3595 [==================>...........] - ETA: 0s - loss: 1.2685 - accuracy: 0.5579 2496/3595 [===================>..........] - ETA: 0s - loss: 1.2588 - accuracy: 0.5589 2624/3595 [====================>.........] - ETA: 0s - loss: 1.2572 - accuracy: 0.5564 2752/3595 [=====================>........] - ETA: 0s - loss: 1.2511 - accuracy: 0.5581 2848/3595 [======================>.......] - ETA: 0s - loss: 1.2460 - accuracy: 0.5600 2976/3595 [=======================>......] - ETA: 0s - loss: 1.2397 - accuracy: 0.5608 3104/3595 [========================>.....] - ETA: 0s - loss: 1.2420 - accuracy: 0.5599 3232/3595 [=========================>....] - ETA: 0s - loss: 1.2494 - accuracy: 0.5582 3360/3595 [===========================>..] - ETA: 0s - loss: 1.2478 - accuracy: 0.5592 3488/3595 [============================>.] - ETA: 0s - loss: 1.2475 - accuracy: 0.5579 3595/3595 [==============================] - 2s 567us/sample - loss: 1.2447 - accuracy: 0.5602 - val_loss: 1.2249 - val_accuracy: 0.5628 Epoch 9/28 32/3595 [..............................] - ETA: 1s - loss: 1.0774 - accuracy: 0.6250 160/3595 [>.............................] - ETA: 2s - loss: 1.2190 - accuracy: 0.5250 288/3595 [=>............................] - ETA: 1s - loss: 1.1769 - accuracy: 0.5590 416/3595 [==>...........................] - ETA: 1s - loss: 1.2330 - accuracy: 0.5361 544/3595 [===>..........................] - ETA: 1s - loss: 1.2331 - accuracy: 0.5551 640/3595 [====>.........................] - ETA: 1s - loss: 1.2264 - accuracy: 0.5547 768/3595 [=====>........................] - ETA: 1s - loss: 1.2213 - accuracy: 0.5638 896/3595 [======>.......................] - ETA: 1s - loss: 1.2271 - accuracy: 0.5658 992/3595 [=======>......................] - ETA: 1s - loss: 1.2249 - accuracy: 0.5625 1120/3595 [========>.....................] - ETA: 1s - loss: 1.2214 - accuracy: 0.5625 1248/3595 [=========>....................] - ETA: 1s - loss: 1.2206 - accuracy: 0.5617 1376/3595 [==========>...................] - ETA: 1s - loss: 1.2245 - accuracy: 0.5610 1472/3595 [===========>..................] - ETA: 1s - loss: 1.2214 - accuracy: 0.5625 1600/3595 [============>.................] - ETA: 1s - loss: 1.2271 - accuracy: 0.5581 1728/3595 [=============>................] - ETA: 0s - loss: 1.2322 - accuracy: 0.5561 1824/3595 [==============>...............] - ETA: 0s - loss: 1.2230 - accuracy: 0.5565 1952/3595 [===============>..............] - ETA: 0s - loss: 1.2152 - accuracy: 0.5610 2080/3595 [================>.............] - ETA: 0s - loss: 1.2032 - accuracy: 0.5668 2208/3595 [=================>............] - ETA: 0s - loss: 1.1978 - accuracy: 0.5657 2304/3595 [==================>...........] - ETA: 0s - loss: 1.2052 - accuracy: 0.5647 2432/3595 [===================>..........] - ETA: 0s - loss: 1.2009 - accuracy: 0.5650 2560/3595 [====================>.........] - ETA: 0s - loss: 1.2064 - accuracy: 0.5609 2688/3595 [=====================>........] - ETA: 0s - loss: 1.2034 - accuracy: 0.5618 2784/3595 [======================>.......] - ETA: 0s - loss: 1.2122 - accuracy: 0.5611 2912/3595 [=======================>......] - ETA: 0s - loss: 1.2080 - accuracy: 0.5622 3040/3595 [========================>.....] - ETA: 0s - loss: 1.2048 - accuracy: 0.5658 3168/3595 [=========================>....] - ETA: 0s - loss: 1.2020 - accuracy: 0.5685 3296/3595 [==========================>...] - ETA: 0s - loss: 1.2028 - accuracy: 0.5680 3424/3595 [===========================>..] - ETA: 0s - loss: 1.2068 - accuracy: 0.5686 3552/3595 [============================>.] - ETA: 0s - loss: 1.2083 - accuracy: 0.5681 3595/3595 [==============================] - 2s 552us/sample - loss: 1.2056 - accuracy: 0.5691 - val_loss: 1.2052 - val_accuracy: 0.5551 Epoch 10/28 32/3595 [..............................] - ETA: 1s - loss: 1.2775 - accuracy: 0.4375 160/3595 [>.............................] - ETA: 1s - loss: 1.2673 - accuracy: 0.4875 288/3595 [=>............................] - ETA: 1s - loss: 1.2266 - accuracy: 0.5556 384/3595 [==>...........................] - ETA: 1s - loss: 1.1745 - accuracy: 0.5807 512/3595 [===>..........................] - ETA: 1s - loss: 1.1569 - accuracy: 0.5918 640/3595 [====>.........................] - ETA: 1s - loss: 1.1393 - accuracy: 0.6078 768/3595 [=====>........................] - ETA: 1s - loss: 1.1391 - accuracy: 0.6055 864/3595 [======>.......................] - ETA: 1s - loss: 1.1224 - accuracy: 0.6111 992/3595 [=======>......................] - ETA: 1s - loss: 1.1412 - accuracy: 0.6038 1120/3595 [========>.....................] - ETA: 1s - loss: 1.1278 - accuracy: 0.6125 1216/3595 [=========>....................] - ETA: 1s - loss: 1.1191 - accuracy: 0.6151 1344/3595 [==========>...................] - ETA: 1s - loss: 1.1329 - accuracy: 0.6124 1472/3595 [===========>..................] - ETA: 1s - loss: 1.1220 - accuracy: 0.6101 1600/3595 [============>.................] - ETA: 1s - loss: 1.1191 - accuracy: 0.6156 1728/3595 [=============>................] - ETA: 0s - loss: 1.1259 - accuracy: 0.6105 1856/3595 [==============>...............] - ETA: 0s - loss: 1.1362 - accuracy: 0.6083 1952/3595 [===============>..............] - ETA: 0s - loss: 1.1337 - accuracy: 0.6060 2080/3595 [================>.............] - ETA: 0s - loss: 1.1370 - accuracy: 0.6034 2208/3595 [=================>............] - ETA: 0s - loss: 1.1508 - accuracy: 0.5992 2336/3595 [==================>...........] - ETA: 0s - loss: 1.1451 - accuracy: 0.6015 2464/3595 [===================>..........] - ETA: 0s - loss: 1.1488 - accuracy: 0.5986 2592/3595 [====================>.........] - ETA: 0s - loss: 1.1485 - accuracy: 0.5972 2688/3595 [=====================>........] - ETA: 0s - loss: 1.1518 - accuracy: 0.5949 2816/3595 [======================>.......] - ETA: 0s - loss: 1.1572 - accuracy: 0.5916 2944/3595 [=======================>......] - ETA: 0s - loss: 1.1579 - accuracy: 0.5890 3072/3595 [========================>.....] - ETA: 0s - loss: 1.1538 - accuracy: 0.5908 3200/3595 [=========================>....] - ETA: 0s - loss: 1.1538 - accuracy: 0.5913 3296/3595 [==========================>...] - ETA: 0s - loss: 1.1539 - accuracy: 0.5916 3424/3595 [===========================>..] - ETA: 0s - loss: 1.1486 - accuracy: 0.5929 3552/3595 [============================>.] - ETA: 0s - loss: 1.1491 - accuracy: 0.5940 3595/3595 [==============================] - 2s 543us/sample - loss: 1.1475 - accuracy: 0.5942 - val_loss: 1.1788 - val_accuracy: 0.5729 Epoch 11/28 32/3595 [..............................] - ETA: 3s - loss: 1.0491 - accuracy: 0.7188 160/3595 [>.............................] - ETA: 2s - loss: 0.9597 - accuracy: 0.7188 288/3595 [=>............................] - ETA: 1s - loss: 1.0021 - accuracy: 0.6771 384/3595 [==>...........................] - ETA: 1s - loss: 0.9519 - accuracy: 0.6849 512/3595 [===>..........................] - ETA: 1s - loss: 0.9642 - accuracy: 0.6738 640/3595 [====>.........................] - ETA: 1s - loss: 0.9844 - accuracy: 0.6609 768/3595 [=====>........................] - ETA: 1s - loss: 1.0033 - accuracy: 0.6471 864/3595 [======>.......................] - ETA: 1s - loss: 1.0234 - accuracy: 0.6366 960/3595 [=======>......................] - ETA: 1s - loss: 1.0503 - accuracy: 0.6302 1056/3595 [=======>......................] - ETA: 1s - loss: 1.0540 - accuracy: 0.6288 1152/3595 [========>.....................] - ETA: 1s - loss: 1.0555 - accuracy: 0.6259 1280/3595 [=========>....................] - ETA: 1s - loss: 1.0547 - accuracy: 0.6281 1408/3595 [==========>...................] - ETA: 1s - loss: 1.0466 - accuracy: 0.6257 1504/3595 [===========>..................] - ETA: 1s - loss: 1.0389 - accuracy: 0.6330 1632/3595 [============>.................] - ETA: 1s - loss: 1.0439 - accuracy: 0.6330 1760/3595 [=============>................] - ETA: 1s - loss: 1.0456 - accuracy: 0.6301 1888/3595 [==============>...............] - ETA: 0s - loss: 1.0462 - accuracy: 0.6329 2016/3595 [===============>..............] - ETA: 0s - loss: 1.0417 - accuracy: 0.6329 2112/3595 [================>.............] - ETA: 0s - loss: 1.0409 - accuracy: 0.6316 2240/3595 [=================>............] - ETA: 0s - loss: 1.0509 - accuracy: 0.6259 2368/3595 [==================>...........] - ETA: 0s - loss: 1.0645 - accuracy: 0.6216 2496/3595 [===================>..........] - ETA: 0s - loss: 1.0617 - accuracy: 0.6214 2624/3595 [====================>.........] - ETA: 0s - loss: 1.0549 - accuracy: 0.6223 2752/3595 [=====================>........] - ETA: 0s - loss: 1.0621 - accuracy: 0.6177 2880/3595 [=======================>......] - ETA: 0s - loss: 1.0582 - accuracy: 0.6191 3008/3595 [========================>.....] - ETA: 0s - loss: 1.0550 - accuracy: 0.6223 3136/3595 [=========================>....] - ETA: 0s - loss: 1.0571 - accuracy: 0.6215 3264/3595 [==========================>...] - ETA: 0s - loss: 1.0616 - accuracy: 0.6186 3392/3595 [===========================>..] - ETA: 0s - loss: 1.0664 - accuracy: 0.6167 3520/3595 [============================>.] - ETA: 0s - loss: 1.0681 - accuracy: 0.6176 3595/3595 [==============================] - 2s 565us/sample - loss: 1.0675 - accuracy: 0.6181 - val_loss: 1.1431 - val_accuracy: 0.5829 Epoch 12/28 32/3595 [..............................] - ETA: 1s - loss: 0.9070 - accuracy: 0.6250 160/3595 [>.............................] - ETA: 2s - loss: 1.0218 - accuracy: 0.6313 288/3595 [=>............................] - ETA: 1s - loss: 1.0815 - accuracy: 0.6181 416/3595 [==>...........................] - ETA: 1s - loss: 1.0407 - accuracy: 0.6274 544/3595 [===>..........................] - ETA: 1s - loss: 1.0328 - accuracy: 0.6176 640/3595 [====>.........................] - ETA: 1s - loss: 1.0540 - accuracy: 0.6156 768/3595 [=====>........................] - ETA: 1s - loss: 1.0673 - accuracy: 0.6159 896/3595 [======>.......................] - ETA: 1s - loss: 1.0901 - accuracy: 0.6038 1024/3595 [=======>......................] - ETA: 1s - loss: 1.0703 - accuracy: 0.6133 1152/3595 [========>.....................] - ETA: 1s - loss: 1.0686 - accuracy: 0.6163 1280/3595 [=========>....................] - ETA: 1s - loss: 1.0694 - accuracy: 0.6109 1376/3595 [==========>...................] - ETA: 1s - loss: 1.0833 - accuracy: 0.6134 1504/3595 [===========>..................] - ETA: 1s - loss: 1.0791 - accuracy: 0.6164 1600/3595 [============>.................] - ETA: 1s - loss: 1.0740 - accuracy: 0.6175 1728/3595 [=============>................] - ETA: 0s - loss: 1.0653 - accuracy: 0.6186 1856/3595 [==============>...............] - ETA: 0s - loss: 1.0535 - accuracy: 0.6239 1952/3595 [===============>..............] - ETA: 0s - loss: 1.0540 - accuracy: 0.6219 2080/3595 [================>.............] - ETA: 0s - loss: 1.0426 - accuracy: 0.6269 2208/3595 [=================>............] - ETA: 0s - loss: 1.0408 - accuracy: 0.6277 2336/3595 [==================>...........] - ETA: 0s - loss: 1.0398 - accuracy: 0.6267 2464/3595 [===================>..........] - ETA: 0s - loss: 1.0298 - accuracy: 0.6323 2592/3595 [====================>.........] - ETA: 0s - loss: 1.0326 - accuracy: 0.6304 2720/3595 [=====================>........] - ETA: 0s - loss: 1.0328 - accuracy: 0.6283 2848/3595 [======================>.......] - ETA: 0s - loss: 1.0334 - accuracy: 0.6268 2944/3595 [=======================>......] - ETA: 0s - loss: 1.0327 - accuracy: 0.6274 3072/3595 [========================>.....] - ETA: 0s - loss: 1.0295 - accuracy: 0.6299 3200/3595 [=========================>....] - ETA: 0s - loss: 1.0311 - accuracy: 0.6297 3328/3595 [==========================>...] - ETA: 0s - loss: 1.0271 - accuracy: 0.6313 3456/3595 [===========================>..] - ETA: 0s - loss: 1.0277 - accuracy: 0.6325 3584/3595 [============================>.] - ETA: 0s - loss: 1.0242 - accuracy: 0.6345 3595/3595 [==============================] - 2s 542us/sample - loss: 1.0242 - accuracy: 0.6342 - val_loss: 1.1342 - val_accuracy: 0.5862 Epoch 13/28 32/3595 [..............................] - ETA: 1s - loss: 1.2758 - accuracy: 0.5625 160/3595 [>.............................] - ETA: 1s - loss: 1.0672 - accuracy: 0.6625 288/3595 [=>............................] - ETA: 1s - loss: 1.0278 - accuracy: 0.6632 416/3595 [==>...........................] - ETA: 1s - loss: 0.9829 - accuracy: 0.6731 544/3595 [===>..........................] - ETA: 1s - loss: 1.0015 - accuracy: 0.6636 672/3595 [====>.........................] - ETA: 1s - loss: 1.0137 - accuracy: 0.6533 800/3595 [=====>........................] - ETA: 1s - loss: 1.0101 - accuracy: 0.6525 928/3595 [======>.......................] - ETA: 1s - loss: 1.0142 - accuracy: 0.6530 1056/3595 [=======>......................] - ETA: 1s - loss: 1.0384 - accuracy: 0.6402 1184/3595 [========>.....................] - ETA: 1s - loss: 1.0302 - accuracy: 0.6470 1312/3595 [=========>....................] - ETA: 1s - loss: 1.0166 - accuracy: 0.6532 1440/3595 [===========>..................] - ETA: 1s - loss: 1.0202 - accuracy: 0.6514 1568/3595 [============>.................] - ETA: 1s - loss: 1.0143 - accuracy: 0.6537 1696/3595 [=============>................] - ETA: 0s - loss: 1.0179 - accuracy: 0.6504 1792/3595 [=============>................] - ETA: 0s - loss: 1.0217 - accuracy: 0.6490 1920/3595 [===============>..............] - ETA: 0s - loss: 1.0172 - accuracy: 0.6490 2048/3595 [================>.............] - ETA: 0s - loss: 1.0099 - accuracy: 0.6499 2176/3595 [=================>............] - ETA: 0s - loss: 1.0012 - accuracy: 0.6526 2304/3595 [==================>...........] - ETA: 0s - loss: 0.9966 - accuracy: 0.6523 2432/3595 [===================>..........] - ETA: 0s - loss: 0.9978 - accuracy: 0.6505 2528/3595 [====================>.........] - ETA: 0s - loss: 0.9951 - accuracy: 0.6527 2656/3595 [=====================>........] - ETA: 0s - loss: 0.9881 - accuracy: 0.6532 2784/3595 [======================>.......] - ETA: 0s - loss: 0.9928 - accuracy: 0.6534 2912/3595 [=======================>......] - ETA: 0s - loss: 0.9908 - accuracy: 0.6525 3040/3595 [========================>.....] - ETA: 0s - loss: 0.9973 - accuracy: 0.6484 3168/3595 [=========================>....] - ETA: 0s - loss: 1.0007 - accuracy: 0.6458 3296/3595 [==========================>...] - ETA: 0s - loss: 0.9948 - accuracy: 0.6462 3424/3595 [===========================>..] - ETA: 0s - loss: 0.9938 - accuracy: 0.6466 3552/3595 [============================>.] - ETA: 0s - loss: 0.9924 - accuracy: 0.6467 3595/3595 [==============================] - 2s 552us/sample - loss: 0.9924 - accuracy: 0.6451 - val_loss: 1.1192 - val_accuracy: 0.5873 Epoch 14/28 32/3595 [..............................] - ETA: 3s - loss: 0.7453 - accuracy: 0.7812 160/3595 [>.............................] - ETA: 2s - loss: 0.9168 - accuracy: 0.7063 288/3595 [=>............................] - ETA: 2s - loss: 0.9799 - accuracy: 0.6771 416/3595 [==>...........................] - ETA: 1s - loss: 0.9818 - accuracy: 0.6659 544/3595 [===>..........................] - ETA: 1s - loss: 0.9766 - accuracy: 0.6691 672/3595 [====>.........................] - ETA: 1s - loss: 0.9746 - accuracy: 0.6667 800/3595 [=====>........................] - ETA: 1s - loss: 0.9758 - accuracy: 0.6712 928/3595 [======>.......................] - ETA: 1s - loss: 0.9862 - accuracy: 0.6627 1056/3595 [=======>......................] - ETA: 1s - loss: 0.9817 - accuracy: 0.6657 1184/3595 [========>.....................] - ETA: 1s - loss: 0.9735 - accuracy: 0.6613 1312/3595 [=========>....................] - ETA: 1s - loss: 0.9710 - accuracy: 0.6616 1440/3595 [===========>..................] - ETA: 1s - loss: 0.9651 - accuracy: 0.6639 1568/3595 [============>.................] - ETA: 1s - loss: 0.9648 - accuracy: 0.6671 1696/3595 [=============>................] - ETA: 1s - loss: 0.9753 - accuracy: 0.6633 1824/3595 [==============>...............] - ETA: 0s - loss: 0.9724 - accuracy: 0.6672 1952/3595 [===============>..............] - ETA: 0s - loss: 0.9661 - accuracy: 0.6691 2080/3595 [================>.............] - ETA: 0s - loss: 0.9665 - accuracy: 0.6707 2208/3595 [=================>............] - ETA: 0s - loss: 0.9683 - accuracy: 0.6698 2336/3595 [==================>...........] - ETA: 0s - loss: 0.9724 - accuracy: 0.6665 2432/3595 [===================>..........] - ETA: 0s - loss: 0.9710 - accuracy: 0.6657 2560/3595 [====================>.........] - ETA: 0s - loss: 0.9687 - accuracy: 0.6680 2688/3595 [=====================>........] - ETA: 0s - loss: 0.9660 - accuracy: 0.6693 2816/3595 [======================>.......] - ETA: 0s - loss: 0.9684 - accuracy: 0.6673 2944/3595 [=======================>......] - ETA: 0s - loss: 0.9665 - accuracy: 0.6668 3072/3595 [========================>.....] - ETA: 0s - loss: 0.9700 - accuracy: 0.6644 3168/3595 [=========================>....] - ETA: 0s - loss: 0.9703 - accuracy: 0.6638 3296/3595 [==========================>...] - ETA: 0s - loss: 0.9676 - accuracy: 0.6650 3424/3595 [===========================>..] - ETA: 0s - loss: 0.9645 - accuracy: 0.6665 3552/3595 [============================>.] - ETA: 0s - loss: 0.9618 - accuracy: 0.6658 3595/3595 [==============================] - 2s 548us/sample - loss: 0.9632 - accuracy: 0.6651 - val_loss: 1.0807 - val_accuracy: 0.6151 Epoch 15/28 32/3595 [..............................] - ETA: 1s - loss: 0.6361 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 1s - loss: 0.8606 - accuracy: 0.6938 288/3595 [=>............................] - ETA: 1s - loss: 0.9109 - accuracy: 0.6806 416/3595 [==>...........................] - ETA: 1s - loss: 0.9091 - accuracy: 0.6923 544/3595 [===>..........................] - ETA: 1s - loss: 0.8823 - accuracy: 0.7059 672/3595 [====>.........................] - ETA: 1s - loss: 0.8886 - accuracy: 0.7009 800/3595 [=====>........................] - ETA: 1s - loss: 0.9013 - accuracy: 0.6850 928/3595 [======>.......................] - ETA: 1s - loss: 0.9112 - accuracy: 0.6821 1056/3595 [=======>......................] - ETA: 1s - loss: 0.9143 - accuracy: 0.6818 1184/3595 [========>.....................] - ETA: 1s - loss: 0.9008 - accuracy: 0.6816 1312/3595 [=========>....................] - ETA: 1s - loss: 0.9054 - accuracy: 0.6768 1408/3595 [==========>...................] - ETA: 1s - loss: 0.9090 - accuracy: 0.6783 1536/3595 [===========>..................] - ETA: 1s - loss: 0.9113 - accuracy: 0.6777 1664/3595 [============>.................] - ETA: 0s - loss: 0.9184 - accuracy: 0.6755 1792/3595 [=============>................] - ETA: 0s - loss: 0.9188 - accuracy: 0.6758 1920/3595 [===============>..............] - ETA: 0s - loss: 0.9117 - accuracy: 0.6760 2048/3595 [================>.............] - ETA: 0s - loss: 0.9183 - accuracy: 0.6782 2176/3595 [=================>............] - ETA: 0s - loss: 0.9203 - accuracy: 0.6751 2304/3595 [==================>...........] - ETA: 0s - loss: 0.9154 - accuracy: 0.6766 2432/3595 [===================>..........] - ETA: 0s - loss: 0.9190 - accuracy: 0.6760 2560/3595 [====================>.........] - ETA: 0s - loss: 0.9143 - accuracy: 0.6793 2688/3595 [=====================>........] - ETA: 0s - loss: 0.9163 - accuracy: 0.6775
2022-04-11 22:27:23.768825: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 22:27:23.774662: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 22:27:23.774736: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 22:27:23.774746: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 22:27:23.774752: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 22:27:23.780928: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1)
2816/3595 [======================>.......] - ETA: 0s - loss: 0.9126 - accuracy: 0.6793 2912/3595 [=======================>......] - ETA: 0s - loss: 0.9111 - accuracy: 0.6796 3040/3595 [========================>.....] - ETA: 0s - loss: 0.9107 - accuracy: 0.6806 3168/3595 [=========================>....] - ETA: 0s - loss: 0.9110 - accuracy: 0.6812 3296/3595 [==========================>...] - ETA: 0s - loss: 0.9083 - accuracy: 0.6829 3424/3595 [===========================>..] - ETA: 0s - loss: 0.9044 - accuracy: 0.6837 3552/3595 [============================>.] - ETA: 0s - loss: 0.9028 - accuracy: 0.6836 3595/3595 [==============================] - 2s 543us/sample - loss: 0.9011 - accuracy: 0.6837 - val_loss: 1.0825 - val_accuracy: 0.6185 Epoch 16/28 32/3595 [..............................] - ETA: 1s - loss: 0.6770 - accuracy: 0.7812 160/3595 [>.............................] - ETA: 1s - loss: 0.8803 - accuracy: 0.6938 288/3595 [=>............................] - ETA: 1s - loss: 0.8404 - accuracy: 0.7118 416/3595 [==>...........................] - ETA: 1s - loss: 0.8761 - accuracy: 0.7043 512/3595 [===>..........................] - ETA: 1s - loss: 0.8661 - accuracy: 0.7109 640/3595 [====>.........................] - ETA: 1s - loss: 0.9061 - accuracy: 0.6953 768/3595 [=====>........................] - ETA: 1s - loss: 0.9020 - accuracy: 0.6901 896/3595 [======>.......................] - ETA: 1s - loss: 0.8944 - accuracy: 0.6864 1024/3595 [=======>......................] - ETA: 1s - loss: 0.8939 - accuracy: 0.6885 1120/3595 [========>.....................] - ETA: 1s - loss: 0.9000 - accuracy: 0.6848 1248/3595 [=========>....................] - ETA: 1s - loss: 0.8945 - accuracy: 0.6923 1376/3595 [==========>...................] - ETA: 1s - loss: 0.9051 - accuracy: 0.6831 1504/3595 [===========>..................] - ETA: 1s - loss: 0.9174 - accuracy: 0.6789 1632/3595 [============>.................] - ETA: 0s - loss: 0.9144 - accuracy: 0.6808 1760/3595 [=============>................] - ETA: 0s - loss: 0.9155 - accuracy: 0.6784 1856/3595 [==============>...............] - ETA: 0s - loss: 0.9102 - accuracy: 0.6810 1984/3595 [===============>..............] - ETA: 0s - loss: 0.9031 - accuracy: 0.6840 2112/3595 [================>.............] - ETA: 0s - loss: 0.9020 - accuracy: 0.6832 2240/3595 [=================>............] - ETA: 0s - loss: 0.9015 - accuracy: 0.6871 2368/3595 [==================>...........] - ETA: 0s - loss: 0.9045 - accuracy: 0.6867 2464/3595 [===================>..........] - ETA: 0s - loss: 0.9051 - accuracy: 0.6863 2560/3595 [====================>.........] - ETA: 0s - loss: 0.9102 - accuracy: 0.6852 2688/3595 [=====================>........] - ETA: 0s - loss: 0.9066 - accuracy: 0.6856 2816/3595 [======================>.......] - ETA: 0s - loss: 0.8994 - accuracy: 0.6882 2944/3595 [=======================>......] - ETA: 0s - loss: 0.8969 - accuracy: 0.6889 3072/3595 [========================>.....] - ETA: 0s - loss: 0.8963 - accuracy: 0.6898 3200/3595 [=========================>....] - ETA: 0s - loss: 0.8971 - accuracy: 0.6909 3296/3595 [==========================>...] - ETA: 0s - loss: 0.9007 - accuracy: 0.6878 3424/3595 [===========================>..] - ETA: 0s - loss: 0.8976 - accuracy: 0.6910 3552/3595 [============================>.] - ETA: 0s - loss: 0.8954 - accuracy: 0.6912 3595/3595 [==============================] - 2s 556us/sample - loss: 0.8929 - accuracy: 0.6918 - val_loss: 1.0805 - val_accuracy: 0.6185 Epoch 17/28 32/3595 [..............................] - ETA: 1s - loss: 1.0442 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 1s - loss: 0.9436 - accuracy: 0.6562 256/3595 [=>............................] - ETA: 1s - loss: 0.8952 - accuracy: 0.6719 384/3595 [==>...........................] - ETA: 1s - loss: 0.8136 - accuracy: 0.7109 512/3595 [===>..........................] - ETA: 1s - loss: 0.7853 - accuracy: 0.7344 640/3595 [====>.........................] - ETA: 1s - loss: 0.7951 - accuracy: 0.7312 768/3595 [=====>........................] - ETA: 1s - loss: 0.8043 - accuracy: 0.7305 864/3595 [======>.......................] - ETA: 1s - loss: 0.8130 - accuracy: 0.7280 992/3595 [=======>......................] - ETA: 1s - loss: 0.8498 - accuracy: 0.7117 1120/3595 [========>.....................] - ETA: 1s - loss: 0.8438 - accuracy: 0.7125 1248/3595 [=========>....................] - ETA: 1s - loss: 0.8377 - accuracy: 0.7123 1344/3595 [==========>...................] - ETA: 1s - loss: 0.8220 - accuracy: 0.7173 1472/3595 [===========>..................] - ETA: 1s - loss: 0.8229 - accuracy: 0.7154 1600/3595 [============>.................] - ETA: 1s - loss: 0.8270 - accuracy: 0.7119 1728/3595 [=============>................] - ETA: 0s - loss: 0.8385 - accuracy: 0.7060 1856/3595 [==============>...............] - ETA: 0s - loss: 0.8447 - accuracy: 0.7031 1984/3595 [===============>..............] - ETA: 0s - loss: 0.8507 - accuracy: 0.7041 2112/3595 [================>.............] - ETA: 0s - loss: 0.8558 - accuracy: 0.6998 2240/3595 [=================>............] - ETA: 0s - loss: 0.8633 - accuracy: 0.6973 2336/3595 [==================>...........] - ETA: 0s - loss: 0.8617 - accuracy: 0.6986 2464/3595 [===================>..........] - ETA: 0s - loss: 0.8635 - accuracy: 0.6989 2592/3595 [====================>.........] - ETA: 0s - loss: 0.8625 - accuracy: 0.6991 2720/3595 [=====================>........] - ETA: 0s - loss: 0.8692 - accuracy: 0.6971 2848/3595 [======================>.......] - ETA: 0s - loss: 0.8669 - accuracy: 0.6977 2976/3595 [=======================>......] - ETA: 0s - loss: 0.8693 - accuracy: 0.6976 3104/3595 [========================>.....] - ETA: 0s - loss: 0.8662 - accuracy: 0.6994 3200/3595 [=========================>....] - ETA: 0s - loss: 0.8663 - accuracy: 0.6981 3328/3595 [==========================>...] - ETA: 0s - loss: 0.8678 - accuracy: 0.6995 3456/3595 [===========================>..] - ETA: 0s - loss: 0.8691 - accuracy: 0.6985 3584/3595 [============================>.] - ETA: 0s - loss: 0.8681 - accuracy: 0.6975 3595/3595 [==============================] - 2s 539us/sample - loss: 0.8693 - accuracy: 0.6965 - val_loss: 1.0560 - val_accuracy: 0.6174 Epoch 18/28 32/3595 [..............................] - ETA: 3s - loss: 0.8180 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 2s - loss: 0.8401 - accuracy: 0.7063 288/3595 [=>............................] - ETA: 1s - loss: 0.8330 - accuracy: 0.7049 416/3595 [==>...........................] - ETA: 1s - loss: 0.8038 - accuracy: 0.7188 544/3595 [===>..........................] - ETA: 1s - loss: 0.8106 - accuracy: 0.7077 672/3595 [====>.........................] - ETA: 1s - loss: 0.8000 - accuracy: 0.7143 800/3595 [=====>........................] - ETA: 1s - loss: 0.8026 - accuracy: 0.7100 928/3595 [======>.......................] - ETA: 1s - loss: 0.8292 - accuracy: 0.7037 1024/3595 [=======>......................] - ETA: 1s - loss: 0.8253 - accuracy: 0.7090 1152/3595 [========>.....................] - ETA: 1s - loss: 0.8415 - accuracy: 0.7031 1280/3595 [=========>....................] - ETA: 1s - loss: 0.8384 - accuracy: 0.7000 1408/3595 [==========>...................] - ETA: 1s - loss: 0.8368 - accuracy: 0.7024 1504/3595 [===========>..................] - ETA: 1s - loss: 0.8391 - accuracy: 0.7035 1632/3595 [============>.................] - ETA: 1s - loss: 0.8344 - accuracy: 0.7059 1760/3595 [=============>................] - ETA: 0s - loss: 0.8368 - accuracy: 0.7006 1888/3595 [==============>...............] - ETA: 0s - loss: 0.8407 - accuracy: 0.6986 2016/3595 [===============>..............] - ETA: 0s - loss: 0.8338 - accuracy: 0.7029 2112/3595 [================>.............] - ETA: 0s - loss: 0.8296 - accuracy: 0.7045 2240/3595 [=================>............] - ETA: 0s - loss: 0.8278 - accuracy: 0.7049 2368/3595 [==================>...........] - ETA: 0s - loss: 0.8288 - accuracy: 0.7044 2496/3595 [===================>..........] - ETA: 0s - loss: 0.8302 - accuracy: 0.7035 2624/3595 [====================>.........] - ETA: 0s - loss: 0.8274 - accuracy: 0.7054 2752/3595 [=====================>........] - ETA: 0s - loss: 0.8319 - accuracy: 0.7053 2880/3595 [=======================>......] - ETA: 0s - loss: 0.8279 - accuracy: 0.7083 2976/3595 [=======================>......] - ETA: 0s - loss: 0.8255 - accuracy: 0.7093 3104/3595 [========================>.....] - ETA: 0s - loss: 0.8256 - accuracy: 0.7104 3232/3595 [=========================>....] - ETA: 0s - loss: 0.8277 - accuracy: 0.7119 3360/3595 [===========================>..] - ETA: 0s - loss: 0.8264 - accuracy: 0.7134 3488/3595 [============================>.] - ETA: 0s - loss: 0.8251 - accuracy: 0.7144 3595/3595 [==============================] - 2s 548us/sample - loss: 0.8281 - accuracy: 0.7129 - val_loss: 1.0416 - val_accuracy: 0.6251 Epoch 19/28 32/3595 [..............................] - ETA: 1s - loss: 0.8099 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 1s - loss: 0.6618 - accuracy: 0.7500 256/3595 [=>............................] - ETA: 1s - loss: 0.6424 - accuracy: 0.7617 384/3595 [==>...........................] - ETA: 1s - loss: 0.7470 - accuracy: 0.7474 480/3595 [===>..........................] - ETA: 1s - loss: 0.7247 - accuracy: 0.7583 608/3595 [====>.........................] - ETA: 1s - loss: 0.7097 - accuracy: 0.7664 736/3595 [=====>........................] - ETA: 1s - loss: 0.7334 - accuracy: 0.7568 864/3595 [======>.......................] - ETA: 1s - loss: 0.7204 - accuracy: 0.7569 960/3595 [=======>......................] - ETA: 1s - loss: 0.7271 - accuracy: 0.7521 1088/3595 [========>.....................] - ETA: 1s - loss: 0.7355 - accuracy: 0.7500 1216/3595 [=========>....................] - ETA: 1s - loss: 0.7475 - accuracy: 0.7475 1344/3595 [==========>...................] - ETA: 1s - loss: 0.7427 - accuracy: 0.7485 1472/3595 [===========>..................] - ETA: 1s - loss: 0.7418 - accuracy: 0.7507 1568/3595 [============>.................] - ETA: 1s - loss: 0.7410 - accuracy: 0.7532 1664/3595 [============>.................] - ETA: 1s - loss: 0.7432 - accuracy: 0.7530 1792/3595 [=============>................] - ETA: 1s - loss: 0.7380 - accuracy: 0.7528 1920/3595 [===============>..............] - ETA: 0s - loss: 0.7404 - accuracy: 0.7521 2048/3595 [================>.............] - ETA: 0s - loss: 0.7430 - accuracy: 0.7500 2176/3595 [=================>............] - ETA: 0s - loss: 0.7452 - accuracy: 0.7514 2304/3595 [==================>...........] - ETA: 0s - loss: 0.7472 - accuracy: 0.7491 2432/3595 [===================>..........] - ETA: 0s - loss: 0.7522 - accuracy: 0.7475 2560/3595 [====================>.........] - ETA: 0s - loss: 0.7604 - accuracy: 0.7445 2656/3595 [=====================>........] - ETA: 0s - loss: 0.7580 - accuracy: 0.7444 2784/3595 [======================>.......] - ETA: 0s - loss: 0.7626 - accuracy: 0.7414 2912/3595 [=======================>......] - ETA: 0s - loss: 0.7630 - accuracy: 0.7411 3040/3595 [========================>.....] - ETA: 0s - loss: 0.7627 - accuracy: 0.7408 3168/3595 [=========================>....] - ETA: 0s - loss: 0.7628 - accuracy: 0.7415 3296/3595 [==========================>...] - ETA: 0s - loss: 0.7685 - accuracy: 0.7388 3392/3595 [===========================>..] - ETA: 0s - loss: 0.7662 - accuracy: 0.7400 3520/3595 [============================>.] - ETA: 0s - loss: 0.7649 - accuracy: 0.7398 3595/3595 [==============================] - 2s 565us/sample - loss: 0.7681 - accuracy: 0.7382 - val_loss: 1.0316 - val_accuracy: 0.6218 Epoch 20/28 32/3595 [..............................] - ETA: 1s - loss: 0.8328 - accuracy: 0.7188 128/3595 [>.............................] - ETA: 2s - loss: 0.8453 - accuracy: 0.6875 256/3595 [=>............................] - ETA: 1s - loss: 0.8303 - accuracy: 0.7148 384/3595 [==>...........................] - ETA: 1s - loss: 0.8198 - accuracy: 0.7240 512/3595 [===>..........................] - ETA: 1s - loss: 0.7705 - accuracy: 0.7363 608/3595 [====>.........................] - ETA: 1s - loss: 0.7787 - accuracy: 0.7319 736/3595 [=====>........................] - ETA: 1s - loss: 0.7745 - accuracy: 0.7337 864/3595 [======>.......................] - ETA: 1s - loss: 0.7596 - accuracy: 0.7442 960/3595 [=======>......................] - ETA: 1s - loss: 0.7667 - accuracy: 0.7427 1088/3595 [========>.....................] - ETA: 1s - loss: 0.7765 - accuracy: 0.7335 1216/3595 [=========>....................] - ETA: 1s - loss: 0.7819 - accuracy: 0.7278 1344/3595 [==========>...................] - ETA: 1s - loss: 0.7724 - accuracy: 0.7314 1472/3595 [===========>..................] - ETA: 1s - loss: 0.7656 - accuracy: 0.7344 1600/3595 [============>.................] - ETA: 1s - loss: 0.7704 - accuracy: 0.7331 1728/3595 [=============>................] - ETA: 0s - loss: 0.7756 - accuracy: 0.7292 1856/3595 [==============>...............] - ETA: 0s - loss: 0.7705 - accuracy: 0.7311 1984/3595 [===============>..............] - ETA: 0s - loss: 0.7704 - accuracy: 0.7308 2112/3595 [================>.............] - ETA: 0s - loss: 0.7641 - accuracy: 0.7344 2240/3595 [=================>............] - ETA: 0s - loss: 0.7602 - accuracy: 0.7362 2368/3595 [==================>...........] - ETA: 0s - loss: 0.7580 - accuracy: 0.7369 2464/3595 [===================>..........] - ETA: 0s - loss: 0.7566 - accuracy: 0.7366 2592/3595 [====================>.........] - ETA: 0s - loss: 0.7564 - accuracy: 0.7373 2720/3595 [=====================>........] - ETA: 0s - loss: 0.7661 - accuracy: 0.7335 2848/3595 [======================>.......] - ETA: 0s - loss: 0.7708 - accuracy: 0.7300 2976/3595 [=======================>......] - ETA: 0s - loss: 0.7715 - accuracy: 0.7298 3104/3595 [========================>.....] - ETA: 0s - loss: 0.7650 - accuracy: 0.7332 3232/3595 [=========================>....] - ETA: 0s - loss: 0.7695 - accuracy: 0.7311 3360/3595 [===========================>..] - ETA: 0s - loss: 0.7632 - accuracy: 0.7345 3488/3595 [============================>.] - ETA: 0s - loss: 0.7617 - accuracy: 0.7354 3595/3595 [==============================] - 2s 548us/sample - loss: 0.7667 - accuracy: 0.7332 - val_loss: 1.0349 - val_accuracy: 0.6151 Epoch 21/28 32/3595 [..............................] - ETA: 1s - loss: 0.8308 - accuracy: 0.6875 128/3595 [>.............................] - ETA: 2s - loss: 0.7311 - accuracy: 0.7969 256/3595 [=>............................] - ETA: 1s - loss: 0.7394 - accuracy: 0.7461 384/3595 [==>...........................] - ETA: 1s - loss: 0.7527 - accuracy: 0.7318 512/3595 [===>..........................] - ETA: 1s - loss: 0.7479 - accuracy: 0.7363 608/3595 [====>.........................] - ETA: 1s - loss: 0.7421 - accuracy: 0.7467 736/3595 [=====>........................] - ETA: 1s - loss: 0.7388 - accuracy: 0.7459 864/3595 [======>.......................] - ETA: 1s - loss: 0.7419 - accuracy: 0.7431 992/3595 [=======>......................] - ETA: 1s - loss: 0.7634 - accuracy: 0.7319 1120/3595 [========>.....................] - ETA: 1s - loss: 0.7688 - accuracy: 0.7277 1248/3595 [=========>....................] - ETA: 1s - loss: 0.7686 - accuracy: 0.7284 1376/3595 [==========>...................] - ETA: 1s - loss: 0.7660 - accuracy: 0.7311 1504/3595 [===========>..................] - ETA: 1s - loss: 0.7586 - accuracy: 0.7347 1632/3595 [============>.................] - ETA: 1s - loss: 0.7517 - accuracy: 0.7433 1760/3595 [=============>................] - ETA: 0s - loss: 0.7415 - accuracy: 0.7472 1888/3595 [==============>...............] - ETA: 0s - loss: 0.7368 - accuracy: 0.7495 1984/3595 [===============>..............] - ETA: 0s - loss: 0.7332 - accuracy: 0.7515 2112/3595 [================>.............] - ETA: 0s - loss: 0.7308 - accuracy: 0.7543 2240/3595 [=================>............] - ETA: 0s - loss: 0.7318 - accuracy: 0.7531 2336/3595 [==================>...........] - ETA: 0s - loss: 0.7350 - accuracy: 0.7521 2464/3595 [===================>..........] - ETA: 0s - loss: 0.7391 - accuracy: 0.7484 2592/3595 [====================>.........] - ETA: 0s - loss: 0.7404 - accuracy: 0.7461 2720/3595 [=====================>........] - ETA: 0s - loss: 0.7412 - accuracy: 0.7441 2816/3595 [======================>.......] - ETA: 0s - loss: 0.7446 - accuracy: 0.7425 2944/3595 [=======================>......] - ETA: 0s - loss: 0.7452 - accuracy: 0.7432 3072/3595 [========================>.....] - ETA: 0s - loss: 0.7415 - accuracy: 0.7461 3168/3595 [=========================>....] - ETA: 0s - loss: 0.7485 - accuracy: 0.7431 3296/3595 [==========================>...] - ETA: 0s - loss: 0.7484 - accuracy: 0.7442 3424/3595 [===========================>..] - ETA: 0s - loss: 0.7442 - accuracy: 0.7453 3552/3595 [============================>.] - ETA: 0s - loss: 0.7472 - accuracy: 0.7447 3595/3595 [==============================] - 2s 556us/sample - loss: 0.7466 - accuracy: 0.7446 - val_loss: 1.0258 - val_accuracy: 0.6196 Epoch 22/28 32/3595 [..............................] - ETA: 1s - loss: 0.6152 - accuracy: 0.7500 128/3595 [>.............................] - ETA: 2s - loss: 0.7155 - accuracy: 0.7188 224/3595 [>.............................] - ETA: 2s - loss: 0.6860 - accuracy: 0.7455 320/3595 [=>............................] - ETA: 2s - loss: 0.6939 - accuracy: 0.7594 416/3595 [==>...........................] - ETA: 2s - loss: 0.7119 - accuracy: 0.7452 544/3595 [===>..........................] - ETA: 1s - loss: 0.7143 - accuracy: 0.7574 672/3595 [====>.........................] - ETA: 1s - loss: 0.7043 - accuracy: 0.7589 768/3595 [=====>........................] - ETA: 1s - loss: 0.6963 - accuracy: 0.7656 896/3595 [======>.......................] - ETA: 1s - loss: 0.7049 - accuracy: 0.7623 1024/3595 [=======>......................] - ETA: 1s - loss: 0.7039 - accuracy: 0.7588 1152/3595 [========>.....................] - ETA: 1s - loss: 0.7125 - accuracy: 0.7526 1280/3595 [=========>....................] - ETA: 1s - loss: 0.7066 - accuracy: 0.7594 1408/3595 [==========>...................] - ETA: 1s - loss: 0.7018 - accuracy: 0.7628 1536/3595 [===========>..................] - ETA: 1s - loss: 0.6956 - accuracy: 0.7643 1664/3595 [============>.................] - ETA: 1s - loss: 0.7037 - accuracy: 0.7620 1792/3595 [=============>................] - ETA: 0s - loss: 0.7049 - accuracy: 0.7628 1920/3595 [===============>..............] - ETA: 0s - loss: 0.7100 - accuracy: 0.7630 2048/3595 [================>.............] - ETA: 0s - loss: 0.7150 - accuracy: 0.7598 2176/3595 [=================>............] - ETA: 0s - loss: 0.7089 - accuracy: 0.7633 2304/3595 [==================>...........] - ETA: 0s - loss: 0.7133 - accuracy: 0.7635 2400/3595 [===================>..........] - ETA: 0s - loss: 0.7099 - accuracy: 0.7650 2528/3595 [====================>.........] - ETA: 0s - loss: 0.7064 - accuracy: 0.7646 2656/3595 [=====================>........] - ETA: 0s - loss: 0.7110 - accuracy: 0.7639 2784/3595 [======================>.......] - ETA: 0s - loss: 0.7130 - accuracy: 0.7615 2912/3595 [=======================>......] - ETA: 0s - loss: 0.7159 - accuracy: 0.7610 3040/3595 [========================>.....] - ETA: 0s - loss: 0.7156 - accuracy: 0.7605 3136/3595 [=========================>....] - ETA: 0s - loss: 0.7140 - accuracy: 0.7608 3264/3595 [==========================>...] - ETA: 0s - loss: 0.7122 - accuracy: 0.7619 3392/3595 [===========================>..] - ETA: 0s - loss: 0.7135 - accuracy: 0.7600 3520/3595 [============================>.] - ETA: 0s - loss: 0.7168 - accuracy: 0.7582 3595/3595 [==============================] - 2s 561us/sample - loss: 0.7159 - accuracy: 0.7583 - val_loss: 1.0143 - val_accuracy: 0.6251 Epoch 23/28 32/3595 [..............................] - ETA: 1s - loss: 0.7699 - accuracy: 0.7188 160/3595 [>.............................] - ETA: 2s - loss: 0.7307 - accuracy: 0.7500 288/3595 [=>............................] - ETA: 1s - loss: 0.6474 - accuracy: 0.7917 416/3595 [==>...........................] - ETA: 1s - loss: 0.6996 - accuracy: 0.7620 544/3595 [===>..........................] - ETA: 1s - loss: 0.7104 - accuracy: 0.7629 640/3595 [====>.........................] - ETA: 1s - loss: 0.7079 - accuracy: 0.7594 768/3595 [=====>........................] - ETA: 1s - loss: 0.6920 - accuracy: 0.7708 896/3595 [======>.......................] - ETA: 1s - loss: 0.7012 - accuracy: 0.7679 1024/3595 [=======>......................] - ETA: 1s - loss: 0.7045 - accuracy: 0.7637 1152/3595 [========>.....................] - ETA: 1s - loss: 0.6955 - accuracy: 0.7639 1280/3595 [=========>....................] - ETA: 1s - loss: 0.6977 - accuracy: 0.7602 1408/3595 [==========>...................] - ETA: 1s - loss: 0.7008 - accuracy: 0.7607 1504/3595 [===========>..................] - ETA: 1s - loss: 0.7020 - accuracy: 0.7606 1632/3595 [============>.................] - ETA: 1s - loss: 0.6947 - accuracy: 0.7623 1760/3595 [=============>................] - ETA: 0s - loss: 0.7003 - accuracy: 0.7591 1856/3595 [==============>...............] - ETA: 0s - loss: 0.6968 - accuracy: 0.7602 1984/3595 [===============>..............] - ETA: 0s - loss: 0.6932 - accuracy: 0.7636 2112/3595 [================>.............] - ETA: 0s - loss: 0.7050 - accuracy: 0.7562 2240/3595 [=================>............] - ETA: 0s - loss: 0.7082 - accuracy: 0.7571 2336/3595 [==================>...........] - ETA: 0s - loss: 0.7044 - accuracy: 0.7594 2464/3595 [===================>..........] - ETA: 0s - loss: 0.7026 - accuracy: 0.7597 2592/3595 [====================>.........] - ETA: 0s - loss: 0.7089 - accuracy: 0.7569 2720/3595 [=====================>........] - ETA: 0s - loss: 0.7069 - accuracy: 0.7585 2816/3595 [======================>.......] - ETA: 0s - loss: 0.7075 - accuracy: 0.7589 2944/3595 [=======================>......] - ETA: 0s - loss: 0.7035 - accuracy: 0.7605 3072/3595 [========================>.....] - ETA: 0s - loss: 0.6977 - accuracy: 0.7627 3200/3595 [=========================>....] - ETA: 0s - loss: 0.6915 - accuracy: 0.7650 3328/3595 [==========================>...] - ETA: 0s - loss: 0.6885 - accuracy: 0.7668 3456/3595 [===========================>..] - ETA: 0s - loss: 0.6834 - accuracy: 0.7688 3552/3595 [============================>.] - ETA: 0s - loss: 0.6811 - accuracy: 0.7703 3595/3595 [==============================] - 2s 552us/sample - loss: 0.6830 - accuracy: 0.7700 - val_loss: 1.0119 - val_accuracy: 0.6296 Epoch 24/28 32/3595 [..............................] - ETA: 1s - loss: 0.8429 - accuracy: 0.7188 160/3595 [>.............................] - ETA: 2s - loss: 0.6008 - accuracy: 0.8125 288/3595 [=>............................] - ETA: 1s - loss: 0.6377 - accuracy: 0.7847 416/3595 [==>...........................] - ETA: 1s - loss: 0.6484 - accuracy: 0.7740 544/3595 [===>..........................] - ETA: 1s - loss: 0.6545 - accuracy: 0.7702 672/3595 [====>.........................] - ETA: 1s - loss: 0.6481 - accuracy: 0.7768 800/3595 [=====>........................] - ETA: 1s - loss: 0.6474 - accuracy: 0.7812 928/3595 [======>.......................] - ETA: 1s - loss: 0.6298 - accuracy: 0.7823 1024/3595 [=======>......................] - ETA: 1s - loss: 0.6304 - accuracy: 0.7822 1152/3595 [========>.....................] - ETA: 1s - loss: 0.6372 - accuracy: 0.7821 1280/3595 [=========>....................] - ETA: 1s - loss: 0.6396 - accuracy: 0.7820 1408/3595 [==========>...................] - ETA: 1s - loss: 0.6347 - accuracy: 0.7834 1536/3595 [===========>..................] - ETA: 1s - loss: 0.6486 - accuracy: 0.7799 1664/3595 [============>.................] - ETA: 0s - loss: 0.6467 - accuracy: 0.7800 1792/3595 [=============>................] - ETA: 0s - loss: 0.6568 - accuracy: 0.7757 1920/3595 [===============>..............] - ETA: 0s - loss: 0.6647 - accuracy: 0.7703 2048/3595 [================>.............] - ETA: 0s - loss: 0.6623 - accuracy: 0.7725 2144/3595 [================>.............] - ETA: 0s - loss: 0.6699 - accuracy: 0.7715 2272/3595 [=================>............] - ETA: 0s - loss: 0.6705 - accuracy: 0.7707 2400/3595 [===================>..........] - ETA: 0s - loss: 0.6660 - accuracy: 0.7742 2528/3595 [====================>.........] - ETA: 0s - loss: 0.6609 - accuracy: 0.7761 2656/3595 [=====================>........] - ETA: 0s - loss: 0.6552 - accuracy: 0.7786 2784/3595 [======================>.......] - ETA: 0s - loss: 0.6523 - accuracy: 0.7816 2880/3595 [=======================>......] - ETA: 0s - loss: 0.6549 - accuracy: 0.7816 3008/3595 [========================>.....] - ETA: 0s - loss: 0.6565 - accuracy: 0.7826 3136/3595 [=========================>....] - ETA: 0s - loss: 0.6576 - accuracy: 0.7822 3264/3595 [==========================>...] - ETA: 0s - loss: 0.6582 - accuracy: 0.7819 3392/3595 [===========================>..] - ETA: 0s - loss: 0.6564 - accuracy: 0.7827 3520/3595 [============================>.] - ETA: 0s - loss: 0.6559 - accuracy: 0.7827 3595/3595 [==============================] - 2s 556us/sample - loss: 0.6552 - accuracy: 0.7825 - val_loss: 1.0041 - val_accuracy: 0.6340 Epoch 25/28 32/3595 [..............................] - ETA: 1s - loss: 0.6437 - accuracy: 0.8125 160/3595 [>.............................] - ETA: 2s - loss: 0.7289 - accuracy: 0.7563 288/3595 [=>............................] - ETA: 1s - loss: 0.7006 - accuracy: 0.7639 416/3595 [==>...........................] - ETA: 1s - loss: 0.6738 - accuracy: 0.7740 544/3595 [===>..........................] - ETA: 1s - loss: 0.6405 - accuracy: 0.7849 640/3595 [====>.........................] - ETA: 1s - loss: 0.6448 - accuracy: 0.7844 768/3595 [=====>........................] - ETA: 1s - loss: 0.6300 - accuracy: 0.7852 896/3595 [======>.......................] - ETA: 1s - loss: 0.6386 - accuracy: 0.7768 992/3595 [=======>......................] - ETA: 1s - loss: 0.6371 - accuracy: 0.7772 1120/3595 [========>.....................] - ETA: 1s - loss: 0.6468 - accuracy: 0.7741 1248/3595 [=========>....................] - ETA: 1s - loss: 0.6460 - accuracy: 0.7756 1376/3595 [==========>...................] - ETA: 1s - loss: 0.6415 - accuracy: 0.7762 1472/3595 [===========>..................] - ETA: 1s - loss: 0.6434 - accuracy: 0.7772 1600/3595 [============>.................] - ETA: 1s - loss: 0.6558 - accuracy: 0.7675 1728/3595 [=============>................] - ETA: 0s - loss: 0.6550 - accuracy: 0.7668 1856/3595 [==============>...............] - ETA: 0s - loss: 0.6558 - accuracy: 0.7699 1984/3595 [===============>..............] - ETA: 0s - loss: 0.6587 - accuracy: 0.7676 2112/3595 [================>.............] - ETA: 0s - loss: 0.6510 - accuracy: 0.7694 2240/3595 [=================>............] - ETA: 0s - loss: 0.6470 - accuracy: 0.7696 2368/3595 [==================>...........] - ETA: 0s - loss: 0.6410 - accuracy: 0.7736 2496/3595 [===================>..........] - ETA: 0s - loss: 0.6380 - accuracy: 0.7756 2624/3595 [====================>.........] - ETA: 0s - loss: 0.6379 - accuracy: 0.7774 2752/3595 [=====================>........] - ETA: 0s - loss: 0.6373 - accuracy: 0.7791 2880/3595 [=======================>......] - ETA: 0s - loss: 0.6396 - accuracy: 0.7792 3008/3595 [========================>.....] - ETA: 0s - loss: 0.6378 - accuracy: 0.7793 3136/3595 [=========================>....] - ETA: 0s - loss: 0.6413 - accuracy: 0.7777 3264/3595 [==========================>...] - ETA: 0s - loss: 0.6455 - accuracy: 0.7760 3392/3595 [===========================>..] - ETA: 0s - loss: 0.6548 - accuracy: 0.7730 3520/3595 [============================>.] - ETA: 0s - loss: 0.6549 - accuracy: 0.7724 3595/3595 [==============================] - 2s 548us/sample - loss: 0.6538 - accuracy: 0.7727 - val_loss: 1.0049 - val_accuracy: 0.6318 Epoch 26/28 32/3595 [..............................] - ETA: 1s - loss: 0.5876 - accuracy: 0.7812 160/3595 [>.............................] - ETA: 1s - loss: 0.5697 - accuracy: 0.7937 256/3595 [=>............................] - ETA: 1s - loss: 0.5991 - accuracy: 0.7969 384/3595 [==>...........................] - ETA: 1s - loss: 0.6113 - accuracy: 0.7917 512/3595 [===>..........................] - ETA: 1s - loss: 0.6013 - accuracy: 0.8066 608/3595 [====>.........................] - ETA: 1s - loss: 0.6092 - accuracy: 0.8026 736/3595 [=====>........................] - ETA: 1s - loss: 0.6046 - accuracy: 0.8003 864/3595 [======>.......................] - ETA: 1s - loss: 0.6060 - accuracy: 0.8021 992/3595 [=======>......................] - ETA: 1s - loss: 0.6169 - accuracy: 0.7964 1120/3595 [========>.....................] - ETA: 1s - loss: 0.6046 - accuracy: 0.7982 1248/3595 [=========>....................] - ETA: 1s - loss: 0.6079 - accuracy: 0.7957 1376/3595 [==========>...................] - ETA: 1s - loss: 0.6177 - accuracy: 0.7951 1472/3595 [===========>..................] - ETA: 1s - loss: 0.6184 - accuracy: 0.7942 1600/3595 [============>.................] - ETA: 1s - loss: 0.6221 - accuracy: 0.7906 1728/3595 [=============>................] - ETA: 0s - loss: 0.6170 - accuracy: 0.7905 1856/3595 [==============>...............] - ETA: 0s - loss: 0.6193 - accuracy: 0.7856 1984/3595 [===============>..............] - ETA: 0s - loss: 0.6152 - accuracy: 0.7888 2112/3595 [================>.............] - ETA: 0s - loss: 0.6147 - accuracy: 0.7898 2240/3595 [=================>............] - ETA: 0s - loss: 0.6092 - accuracy: 0.7911 2368/3595 [==================>...........] - ETA: 0s - loss: 0.6164 - accuracy: 0.7884 2496/3595 [===================>..........] - ETA: 0s - loss: 0.6209 - accuracy: 0.7861 2624/3595 [====================>.........] - ETA: 0s - loss: 0.6254 - accuracy: 0.7862 2720/3595 [=====================>........] - ETA: 0s - loss: 0.6297 - accuracy: 0.7838 2848/3595 [======================>.......] - ETA: 0s - loss: 0.6230 - accuracy: 0.7879 2976/3595 [=======================>......] - ETA: 0s - loss: 0.6231 - accuracy: 0.7863 3104/3595 [========================>.....] - ETA: 0s - loss: 0.6280 - accuracy: 0.7867 3232/3595 [=========================>....] - ETA: 0s - loss: 0.6249 - accuracy: 0.7884 3360/3595 [===========================>..] - ETA: 0s - loss: 0.6251 - accuracy: 0.7878 3456/3595 [===========================>..] - ETA: 0s - loss: 0.6292 - accuracy: 0.7850 3584/3595 [============================>.] - ETA: 0s - loss: 0.6263 - accuracy: 0.7852 3595/3595 [==============================] - 2s 548us/sample - loss: 0.6277 - accuracy: 0.7847 - val_loss: 1.0148 - val_accuracy: 0.6352 Epoch 27/28 32/3595 [..............................] - ETA: 3s - loss: 0.6176 - accuracy: 0.7812 160/3595 [>.............................] - ETA: 2s - loss: 0.7136 - accuracy: 0.7563 288/3595 [=>............................] - ETA: 1s - loss: 0.6608 - accuracy: 0.7639 416/3595 [==>...........................] - ETA: 1s - loss: 0.6237 - accuracy: 0.7837 512/3595 [===>..........................] - ETA: 1s - loss: 0.6061 - accuracy: 0.7910 640/3595 [====>.........................] - ETA: 1s - loss: 0.6108 - accuracy: 0.7891 768/3595 [=====>........................] - ETA: 1s - loss: 0.6254 - accuracy: 0.7786 896/3595 [======>.......................] - ETA: 1s - loss: 0.6265 - accuracy: 0.7812 1024/3595 [=======>......................] - ETA: 1s - loss: 0.6264 - accuracy: 0.7773 1120/3595 [========>.....................] - ETA: 1s - loss: 0.6172 - accuracy: 0.7821 1248/3595 [=========>....................] - ETA: 1s - loss: 0.6309 - accuracy: 0.7804 1376/3595 [==========>...................] - ETA: 1s - loss: 0.6254 - accuracy: 0.7834 1504/3595 [===========>..................] - ETA: 1s - loss: 0.6396 - accuracy: 0.7793 1600/3595 [============>.................] - ETA: 1s - loss: 0.6380 - accuracy: 0.7806 1696/3595 [=============>................] - ETA: 1s - loss: 0.6376 - accuracy: 0.7824 1824/3595 [==============>...............] - ETA: 0s - loss: 0.6281 - accuracy: 0.7889 1920/3595 [===============>..............] - ETA: 0s - loss: 0.6303 - accuracy: 0.7865 2048/3595 [================>.............] - ETA: 0s - loss: 0.6270 - accuracy: 0.7881 2176/3595 [=================>............] - ETA: 0s - loss: 0.6210 - accuracy: 0.7909 2272/3595 [=================>............] - ETA: 0s - loss: 0.6203 - accuracy: 0.7923 2400/3595 [===================>..........] - ETA: 0s - loss: 0.6254 - accuracy: 0.7875 2528/3595 [====================>.........] - ETA: 0s - loss: 0.6293 - accuracy: 0.7856 2656/3595 [=====================>........] - ETA: 0s - loss: 0.6228 - accuracy: 0.7869 2784/3595 [======================>.......] - ETA: 0s - loss: 0.6175 - accuracy: 0.7909 2912/3595 [=======================>......] - ETA: 0s - loss: 0.6154 - accuracy: 0.7926 3008/3595 [========================>.....] - ETA: 0s - loss: 0.6133 - accuracy: 0.7945 3136/3595 [=========================>....] - ETA: 0s - loss: 0.6129 - accuracy: 0.7940 3264/3595 [==========================>...] - ETA: 0s - loss: 0.6170 - accuracy: 0.7923 3392/3595 [===========================>..] - ETA: 0s - loss: 0.6143 - accuracy: 0.7942 3520/3595 [============================>.] - ETA: 0s - loss: 0.6197 - accuracy: 0.7929 3595/3595 [==============================] - 2s 565us/sample - loss: 0.6174 - accuracy: 0.7933 - val_loss: 1.0122 - val_accuracy: 0.6263 Epoch 28/28 32/3595 [..............................] - ETA: 1s - loss: 0.4823 - accuracy: 0.8750 160/3595 [>.............................] - ETA: 1s - loss: 0.5168 - accuracy: 0.8313 256/3595 [=>............................] - ETA: 1s - loss: 0.5601 - accuracy: 0.7969 384/3595 [==>...........................] - ETA: 1s - loss: 0.5523 - accuracy: 0.8021 512/3595 [===>..........................] - ETA: 1s - loss: 0.5379 - accuracy: 0.8105 608/3595 [====>.........................] - ETA: 1s - loss: 0.5424 - accuracy: 0.8141 736/3595 [=====>........................] - ETA: 1s - loss: 0.5572 - accuracy: 0.8084 864/3595 [======>.......................] - ETA: 1s - loss: 0.5711 - accuracy: 0.8056 992/3595 [=======>......................] - ETA: 1s - loss: 0.5748 - accuracy: 0.8054 1088/3595 [========>.....................] - ETA: 1s - loss: 0.5878 - accuracy: 0.8006 1216/3595 [=========>....................] - ETA: 1s - loss: 0.5754 - accuracy: 0.8035 1344/3595 [==========>...................] - ETA: 1s - loss: 0.5766 - accuracy: 0.7984 1472/3595 [===========>..................] - ETA: 1s - loss: 0.5633 - accuracy: 0.8057 1568/3595 [============>.................] - ETA: 1s - loss: 0.5635 - accuracy: 0.8055 1696/3595 [=============>................] - ETA: 0s - loss: 0.5675 - accuracy: 0.8060 1824/3595 [==============>...............] - ETA: 0s - loss: 0.5610 - accuracy: 0.8103 1920/3595 [===============>..............] - ETA: 0s - loss: 0.5671 - accuracy: 0.8083 2048/3595 [================>.............] - ETA: 0s - loss: 0.5680 - accuracy: 0.8096 2176/3595 [=================>............] - ETA: 0s - loss: 0.5695 - accuracy: 0.8102 2272/3595 [=================>............] - ETA: 0s - loss: 0.5701 - accuracy: 0.8094 2400/3595 [===================>..........] - ETA: 0s - loss: 0.5658 - accuracy: 0.8112 2528/3595 [====================>.........] - ETA: 0s - loss: 0.5645 - accuracy: 0.8129 2656/3595 [=====================>........] - ETA: 0s - loss: 0.5709 - accuracy: 0.8121 2752/3595 [=====================>........] - ETA: 0s - loss: 0.5706 - accuracy: 0.8118 2880/3595 [=======================>......] - ETA: 0s - loss: 0.5736 - accuracy: 0.8111 3008/3595 [========================>.....] - ETA: 0s - loss: 0.5719 - accuracy: 0.8122 3136/3595 [=========================>....] - ETA: 0s - loss: 0.5741 - accuracy: 0.8112 3264/3595 [==========================>...] - ETA: 0s - loss: 0.5782 - accuracy: 0.8094 3392/3595 [===========================>..] - ETA: 0s - loss: 0.5786 - accuracy: 0.8084 3520/3595 [============================>.] - ETA: 0s - loss: 0.5796 - accuracy: 0.8085 3595/3595 [==============================] - 2s 556us/sample - loss: 0.5789 - accuracy: 0.8097 - val_loss: 0.9900 - val_accuracy: 0.6329 Evaluating model for iteration 1... 1498/1498 - 0s - loss: 0.9298 - accuracy: 0.6796 Accuracy for iteration 1 0.6795727610588074 Training model for iteration 2... Train on 3595 samples, validate on 899 samples Epoch 1/28 32/3595 [..............................] - ETA: 41s - loss: 3.7020 - accuracy: 0.0312 160/3595 [>.............................] - ETA: 9s - loss: 3.3007 - accuracy: 0.1125 256/3595 [=>............................] - ETA: 6s - loss: 3.3387 - accuracy: 0.0977 416/3595 [==>...........................] - ETA: 4s - loss: 3.3345 - accuracy: 0.0913 544/3595 [===>..........................] - ETA: 3s - loss: 3.2988 - accuracy: 0.1103 672/3595 [====>.........................] - ETA: 2s - loss: 3.2562 - accuracy: 0.1265 800/3595 [=====>........................] - ETA: 2s - loss: 3.2482 - accuracy: 0.1213 928/3595 [======>.......................] - ETA: 2s - loss: 3.2087 - accuracy: 0.1196 1056/3595 [=======>......................] - ETA: 2s - loss: 3.1770 - accuracy: 0.1250 1184/3595 [========>.....................] - ETA: 1s - loss: 3.1496 - accuracy: 0.1267 1344/3595 [==========>...................] - ETA: 1s - loss: 3.1286 - accuracy: 0.1272 1472/3595 [===========>..................] - ETA: 1s - loss: 3.0870 - accuracy: 0.1359 1600/3595 [============>.................] - ETA: 1s - loss: 3.0448 - accuracy: 0.1444 1728/3595 [=============>................] - ETA: 1s - loss: 3.0108 - accuracy: 0.1505 1856/3595 [==============>...............] - ETA: 1s - loss: 2.9616 - accuracy: 0.1573 2016/3595 [===============>..............] - ETA: 1s - loss: 2.9259 - accuracy: 0.1607 2112/3595 [================>.............] - ETA: 0s - loss: 2.9078 - accuracy: 0.1634 2240/3595 [=================>............] - ETA: 0s - loss: 2.8809 - accuracy: 0.1665 2368/3595 [==================>...........] - ETA: 0s - loss: 2.8645 - accuracy: 0.1702 2496/3595 [===================>..........] - ETA: 0s - loss: 2.8352 - accuracy: 0.1787 2656/3595 [=====================>........] - ETA: 0s - loss: 2.8033 - accuracy: 0.1845 2784/3595 [======================>.......] - ETA: 0s - loss: 2.7992 - accuracy: 0.1864 2912/3595 [=======================>......] - ETA: 0s - loss: 2.7721 - accuracy: 0.1892 3008/3595 [========================>.....] - ETA: 0s - loss: 2.7503 - accuracy: 0.1928 3104/3595 [========================>.....] - ETA: 0s - loss: 2.7379 - accuracy: 0.1939 3232/3595 [=========================>....] - ETA: 0s - loss: 2.7208 - accuracy: 0.1993 3360/3595 [===========================>..] - ETA: 0s - loss: 2.7023 - accuracy: 0.2021 3456/3595 [===========================>..] - ETA: 0s - loss: 2.6866 - accuracy: 0.2031 3584/3595 [============================>.] - ETA: 0s - loss: 2.6639 - accuracy: 0.2076 3595/3595 [==============================] - 3s 709us/sample - loss: 2.6629 - accuracy: 0.2075 - val_loss: 2.1348 - val_accuracy: 0.2681 Epoch 2/28 32/3595 [..............................] - ETA: 1s - loss: 2.1097 - accuracy: 0.2812 128/3595 [>.............................] - ETA: 2s - loss: 2.1051 - accuracy: 0.3438 256/3595 [=>............................] - ETA: 1s - loss: 2.0742 - accuracy: 0.3438 384/3595 [==>...........................] - ETA: 1s - loss: 2.0945 - accuracy: 0.3307 512/3595 [===>..........................] - ETA: 1s - loss: 2.1164 - accuracy: 0.3145 640/3595 [====>.........................] - ETA: 1s - loss: 2.0968 - accuracy: 0.3187 768/3595 [=====>........................] - ETA: 1s - loss: 2.1193 - accuracy: 0.3060 896/3595 [======>.......................] - ETA: 1s - loss: 2.0910 - accuracy: 0.3080 992/3595 [=======>......................] - ETA: 1s - loss: 2.0877 - accuracy: 0.3085 1120/3595 [========>.....................] - ETA: 1s - loss: 2.0764 - accuracy: 0.3071 1248/3595 [=========>....................] - ETA: 1s - loss: 2.0698 - accuracy: 0.3141 1376/3595 [==========>...................] - ETA: 1s - loss: 2.0610 - accuracy: 0.3154 1504/3595 [===========>..................] - ETA: 1s - loss: 2.0413 - accuracy: 0.3225 1600/3595 [============>.................] - ETA: 1s - loss: 2.0506 - accuracy: 0.3181 1728/3595 [=============>................] - ETA: 0s - loss: 2.0360 - accuracy: 0.3229 1856/3595 [==============>...............] - ETA: 0s - loss: 2.0335 - accuracy: 0.3222 1984/3595 [===============>..............] - ETA: 0s - loss: 2.0188 - accuracy: 0.3276 2112/3595 [================>.............] - ETA: 0s - loss: 2.0176 - accuracy: 0.3272 2240/3595 [=================>............] - ETA: 0s - loss: 2.0146 - accuracy: 0.3295 2368/3595 [==================>...........] - ETA: 0s - loss: 2.0222 - accuracy: 0.3256 2464/3595 [===================>..........] - ETA: 0s - loss: 2.0271 - accuracy: 0.3235 2592/3595 [====================>.........] - ETA: 0s - loss: 2.0171 - accuracy: 0.3256 2720/3595 [=====================>........] - ETA: 0s - loss: 2.0109 - accuracy: 0.3272 2848/3595 [======================>.......] - ETA: 0s - loss: 2.0014 - accuracy: 0.3308 2976/3595 [=======================>......] - ETA: 0s - loss: 1.9991 - accuracy: 0.3290 3104/3595 [========================>.....] - ETA: 0s - loss: 1.9939 - accuracy: 0.3296 3232/3595 [=========================>....] - ETA: 0s - loss: 1.9862 - accuracy: 0.3320 3360/3595 [===========================>..] - ETA: 0s - loss: 1.9872 - accuracy: 0.3315 3488/3595 [============================>.] - ETA: 0s - loss: 1.9853 - accuracy: 0.3320 3584/3595 [============================>.] - ETA: 0s - loss: 1.9834 - accuracy: 0.3306 3595/3595 [==============================] - 2s 544us/sample - loss: 1.9840 - accuracy: 0.3305 - val_loss: 1.7219 - val_accuracy: 0.3938 Epoch 3/28 32/3595 [..............................] - ETA: 1s - loss: 1.9400 - accuracy: 0.3750 128/3595 [>.............................] - ETA: 2s - loss: 1.8075 - accuracy: 0.3984 256/3595 [=>............................] - ETA: 1s - loss: 1.7585 - accuracy: 0.4062 384/3595 [==>...........................] - ETA: 1s - loss: 1.7946 - accuracy: 0.3984 512/3595 [===>..........................] - ETA: 1s - loss: 1.7693 - accuracy: 0.3984 640/3595 [====>.........................] - ETA: 1s - loss: 1.8054 - accuracy: 0.3891 768/3595 [=====>........................] - ETA: 1s - loss: 1.7945 - accuracy: 0.3945 896/3595 [======>.......................] - ETA: 1s - loss: 1.8028 - accuracy: 0.3895 1024/3595 [=======>......................] - ETA: 1s - loss: 1.7925 - accuracy: 0.3877 1152/3595 [========>.....................] - ETA: 1s - loss: 1.7790 - accuracy: 0.3906 1280/3595 [=========>....................] - ETA: 1s - loss: 1.7820 - accuracy: 0.3930 1408/3595 [==========>...................] - ETA: 1s - loss: 1.7887 - accuracy: 0.3906 1504/3595 [===========>..................] - ETA: 1s - loss: 1.7794 - accuracy: 0.3936 1632/3595 [============>.................] - ETA: 1s - loss: 1.7834 - accuracy: 0.3922 1760/3595 [=============>................] - ETA: 0s - loss: 1.7870 - accuracy: 0.3909 1888/3595 [==============>...............] - ETA: 0s - loss: 1.7760 - accuracy: 0.3941 2016/3595 [===============>..............] - ETA: 0s - loss: 1.7751 - accuracy: 0.3934 2144/3595 [================>.............] - ETA: 0s - loss: 1.7698 - accuracy: 0.3951 2272/3595 [=================>............] - ETA: 0s - loss: 1.7714 - accuracy: 0.3939 2368/3595 [==================>...........] - ETA: 0s - loss: 1.7705 - accuracy: 0.3932 2496/3595 [===================>..........] - ETA: 0s - loss: 1.7780 - accuracy: 0.3906 2624/3595 [====================>.........] - ETA: 0s - loss: 1.7751 - accuracy: 0.3929 2752/3595 [=====================>........] - ETA: 0s - loss: 1.7689 - accuracy: 0.3964 2880/3595 [=======================>......] - ETA: 0s - loss: 1.7712 - accuracy: 0.3965 3008/3595 [========================>.....] - ETA: 0s - loss: 1.7786 - accuracy: 0.3946 3136/3595 [=========================>....] - ETA: 0s - loss: 1.7765 - accuracy: 0.3948 3264/3595 [==========================>...] - ETA: 0s - loss: 1.7731 - accuracy: 0.3934 3392/3595 [===========================>..] - ETA: 0s - loss: 1.7775 - accuracy: 0.3906 3520/3595 [============================>.] - ETA: 0s - loss: 1.7763 - accuracy: 0.3909 3595/3595 [==============================] - 2s 539us/sample - loss: 1.7777 - accuracy: 0.3889 - val_loss: 1.5427 - val_accuracy: 0.4505 Epoch 4/28 32/3595 [..............................] - ETA: 1s - loss: 1.5729 - accuracy: 0.4062 160/3595 [>.............................] - ETA: 1s - loss: 1.5613 - accuracy: 0.4625 256/3595 [=>............................] - ETA: 1s - loss: 1.5323 - accuracy: 0.4766 384/3595 [==>...........................] - ETA: 1s - loss: 1.5611 - accuracy: 0.4557 512/3595 [===>..........................] - ETA: 1s - loss: 1.5884 - accuracy: 0.4473 640/3595 [====>.........................] - ETA: 1s - loss: 1.5751 - accuracy: 0.4469 736/3595 [=====>........................] - ETA: 1s - loss: 1.5638 - accuracy: 0.4470 864/3595 [======>.......................] - ETA: 1s - loss: 1.5697 - accuracy: 0.4387 992/3595 [=======>......................] - ETA: 1s - loss: 1.5541 - accuracy: 0.4516 1120/3595 [========>.....................] - ETA: 1s - loss: 1.5906 - accuracy: 0.4384 1248/3595 [=========>....................] - ETA: 1s - loss: 1.6140 - accuracy: 0.4287 1376/3595 [==========>...................] - ETA: 1s - loss: 1.6178 - accuracy: 0.4259 1472/3595 [===========>..................] - ETA: 1s - loss: 1.6256 - accuracy: 0.4219 1600/3595 [============>.................] - ETA: 1s - loss: 1.6254 - accuracy: 0.4225 1696/3595 [=============>................] - ETA: 1s - loss: 1.6323 - accuracy: 0.4198 1792/3595 [=============>................] - ETA: 0s - loss: 1.6236 - accuracy: 0.4213 1920/3595 [===============>..............] - ETA: 0s - loss: 1.6259 - accuracy: 0.4219 2048/3595 [================>.............] - ETA: 0s - loss: 1.6244 - accuracy: 0.4238 2176/3595 [=================>............] - ETA: 0s - loss: 1.6165 - accuracy: 0.4251 2304/3595 [==================>...........] - ETA: 0s - loss: 1.6039 - accuracy: 0.4301 2400/3595 [===================>..........] - ETA: 0s - loss: 1.5991 - accuracy: 0.4329 2528/3595 [====================>.........] - ETA: 0s - loss: 1.5971 - accuracy: 0.4347 2656/3595 [=====================>........] - ETA: 0s - loss: 1.6011 - accuracy: 0.4334 2784/3595 [======================>.......] - ETA: 0s - loss: 1.6007 - accuracy: 0.4335 2912/3595 [=======================>......] - ETA: 0s - loss: 1.5966 - accuracy: 0.4348 3040/3595 [========================>.....] - ETA: 0s - loss: 1.5961 - accuracy: 0.4352 3168/3595 [=========================>....] - ETA: 0s - loss: 1.5968 - accuracy: 0.4331 3296/3595 [==========================>...] - ETA: 0s - loss: 1.5944 - accuracy: 0.4363 3424/3595 [===========================>..] - ETA: 0s - loss: 1.5900 - accuracy: 0.4366 3520/3595 [============================>.] - ETA: 0s - loss: 1.5886 - accuracy: 0.4375 3595/3595 [==============================] - 2s 557us/sample - loss: 1.5902 - accuracy: 0.4384 - val_loss: 1.4584 - val_accuracy: 0.4761 Epoch 5/28 32/3595 [..............................] - ETA: 1s - loss: 1.4536 - accuracy: 0.5000 160/3595 [>.............................] - ETA: 1s - loss: 1.6260 - accuracy: 0.4187 256/3595 [=>............................] - ETA: 1s - loss: 1.5624 - accuracy: 0.4297 384/3595 [==>...........................] - ETA: 1s - loss: 1.4941 - accuracy: 0.4609 512/3595 [===>..........................] - ETA: 1s - loss: 1.4728 - accuracy: 0.4707 640/3595 [====>.........................] - ETA: 1s - loss: 1.4859 - accuracy: 0.4750 768/3595 [=====>........................] - ETA: 1s - loss: 1.4727 - accuracy: 0.4727 896/3595 [======>.......................] - ETA: 1s - loss: 1.4721 - accuracy: 0.4743 1024/3595 [=======>......................] - ETA: 1s - loss: 1.4870 - accuracy: 0.4795 1152/3595 [========>.....................] - ETA: 1s - loss: 1.4725 - accuracy: 0.4861 1248/3595 [=========>....................] - ETA: 1s - loss: 1.4803 - accuracy: 0.4840 1376/3595 [==========>...................] - ETA: 1s - loss: 1.4694 - accuracy: 0.4906 1504/3595 [===========>..................] - ETA: 1s - loss: 1.4802 - accuracy: 0.4887 1632/3595 [============>.................] - ETA: 0s - loss: 1.4813 - accuracy: 0.4859 1760/3595 [=============>................] - ETA: 0s - loss: 1.4745 - accuracy: 0.4898 1888/3595 [==============>...............] - ETA: 0s - loss: 1.4790 - accuracy: 0.4857 2016/3595 [===============>..............] - ETA: 0s - loss: 1.4874 - accuracy: 0.4816 2144/3595 [================>.............] - ETA: 0s - loss: 1.4979 - accuracy: 0.4771 2272/3595 [=================>............] - ETA: 0s - loss: 1.5020 - accuracy: 0.4758 2400/3595 [===================>..........] - ETA: 0s - loss: 1.4978 - accuracy: 0.4758 2528/3595 [====================>.........] - ETA: 0s - loss: 1.5094 - accuracy: 0.4711 2624/3595 [====================>.........] - ETA: 0s - loss: 1.5062 - accuracy: 0.4741 2752/3595 [=====================>........] - ETA: 0s - loss: 1.5078 - accuracy: 0.4735 2880/3595 [=======================>......] - ETA: 0s - loss: 1.4994 - accuracy: 0.4781 3008/3595 [========================>.....] - ETA: 0s - loss: 1.4971 - accuracy: 0.4801 3136/3595 [=========================>....] - ETA: 0s - loss: 1.4988 - accuracy: 0.4802 3264/3595 [==========================>...] - ETA: 0s - loss: 1.5010 - accuracy: 0.4782 3392/3595 [===========================>..] - ETA: 0s - loss: 1.4911 - accuracy: 0.4817 3520/3595 [============================>.] - ETA: 0s - loss: 1.4936 - accuracy: 0.4815 3595/3595 [==============================] - 2s 535us/sample - loss: 1.4958 - accuracy: 0.4809 - val_loss: 1.3990 - val_accuracy: 0.4972 Epoch 6/28 32/3595 [..............................] - ETA: 1s - loss: 1.3720 - accuracy: 0.5312 160/3595 [>.............................] - ETA: 1s - loss: 1.5848 - accuracy: 0.4500 256/3595 [=>............................] - ETA: 1s - loss: 1.5989 - accuracy: 0.4570 384/3595 [==>...........................] - ETA: 1s - loss: 1.4881 - accuracy: 0.4766 480/3595 [===>..........................] - ETA: 1s - loss: 1.5076 - accuracy: 0.4563 608/3595 [====>.........................] - ETA: 1s - loss: 1.4725 - accuracy: 0.4638 736/3595 [=====>........................] - ETA: 1s - loss: 1.4845 - accuracy: 0.4647 864/3595 [======>.......................] - ETA: 1s - loss: 1.4660 - accuracy: 0.4780 992/3595 [=======>......................] - ETA: 1s - loss: 1.4689 - accuracy: 0.4778 1088/3595 [========>.....................] - ETA: 1s - loss: 1.4594 - accuracy: 0.4835 1216/3595 [=========>....................] - ETA: 1s - loss: 1.4443 - accuracy: 0.4926 1344/3595 [==========>...................] - ETA: 1s - loss: 1.4383 - accuracy: 0.4933 1472/3595 [===========>..................] - ETA: 1s - loss: 1.4220 - accuracy: 0.4980 1600/3595 [============>.................] - ETA: 1s - loss: 1.4091 - accuracy: 0.5019 1728/3595 [=============>................] - ETA: 0s - loss: 1.4161 - accuracy: 0.5000 1824/3595 [==============>...............] - ETA: 0s - loss: 1.4161 - accuracy: 0.5005 1952/3595 [===============>..............] - ETA: 0s - loss: 1.4155 - accuracy: 0.5036 2080/3595 [================>.............] - ETA: 0s - loss: 1.4179 - accuracy: 0.5010 2208/3595 [=================>............] - ETA: 0s - loss: 1.4163 - accuracy: 0.5000 2336/3595 [==================>...........] - ETA: 0s - loss: 1.4134 - accuracy: 0.5004 2432/3595 [===================>..........] - ETA: 0s - loss: 1.4232 - accuracy: 0.4975 2560/3595 [====================>.........] - ETA: 0s - loss: 1.4283 - accuracy: 0.4961 2688/3595 [=====================>........] - ETA: 0s - loss: 1.4212 - accuracy: 0.4989 2816/3595 [======================>.......] - ETA: 0s - loss: 1.4218 - accuracy: 0.4975 2912/3595 [=======================>......] - ETA: 0s - loss: 1.4187 - accuracy: 0.4973 3040/3595 [========================>.....] - ETA: 0s - loss: 1.4151 - accuracy: 0.4990 3168/3595 [=========================>....] - ETA: 0s - loss: 1.4120 - accuracy: 0.4994 3296/3595 [==========================>...] - ETA: 0s - loss: 1.4148 - accuracy: 0.4979 3392/3595 [===========================>..] - ETA: 0s - loss: 1.4132 - accuracy: 0.5000 3520/3595 [============================>.] - ETA: 0s - loss: 1.4182 - accuracy: 0.4983 3595/3595 [==============================] - 2s 548us/sample - loss: 1.4180 - accuracy: 0.4974 - val_loss: 1.3319 - val_accuracy: 0.5206 Epoch 7/28 32/3595 [..............................] - ETA: 1s - loss: 1.3243 - accuracy: 0.5000 160/3595 [>.............................] - ETA: 1s - loss: 1.4696 - accuracy: 0.4625 256/3595 [=>............................] - ETA: 1s - loss: 1.4273 - accuracy: 0.4727 352/3595 [=>............................] - ETA: 1s - loss: 1.4308 - accuracy: 0.4830 448/3595 [==>...........................] - ETA: 1s - loss: 1.4010 - accuracy: 0.4955 576/3595 [===>..........................] - ETA: 1s - loss: 1.3905 - accuracy: 0.4913 704/3595 [====>.........................] - ETA: 1s - loss: 1.3866 - accuracy: 0.4901 832/3595 [=====>........................] - ETA: 1s - loss: 1.3514 - accuracy: 0.5096 960/3595 [=======>......................] - ETA: 1s - loss: 1.3449 - accuracy: 0.5104 1088/3595 [========>.....................] - ETA: 1s - loss: 1.3450 - accuracy: 0.5129 1216/3595 [=========>....................] - ETA: 1s - loss: 1.3478 - accuracy: 0.5123 1344/3595 [==========>...................] - ETA: 1s - loss: 1.3601 - accuracy: 0.5089 1472/3595 [===========>..................] - ETA: 1s - loss: 1.3632 - accuracy: 0.5082 1600/3595 [============>.................] - ETA: 1s - loss: 1.3743 - accuracy: 0.5031 1728/3595 [=============>................] - ETA: 0s - loss: 1.3652 - accuracy: 0.5098 1824/3595 [==============>...............] - ETA: 0s - loss: 1.3561 - accuracy: 0.5137 1952/3595 [===============>..............] - ETA: 0s - loss: 1.3642 - accuracy: 0.5092 2080/3595 [================>.............] - ETA: 0s - loss: 1.3628 - accuracy: 0.5082 2208/3595 [=================>............] - ETA: 0s - loss: 1.3658 - accuracy: 0.5100 2336/3595 [==================>...........] - ETA: 0s - loss: 1.3676 - accuracy: 0.5124 2464/3595 [===================>..........] - ETA: 0s - loss: 1.3640 - accuracy: 0.5134 2592/3595 [====================>.........] - ETA: 0s - loss: 1.3647 - accuracy: 0.5143 2720/3595 [=====================>........] - ETA: 0s - loss: 1.3694 - accuracy: 0.5114 2848/3595 [======================>.......] - ETA: 0s - loss: 1.3700 - accuracy: 0.5112 2944/3595 [=======================>......] - ETA: 0s - loss: 1.3754 - accuracy: 0.5102 3072/3595 [========================>.....] - ETA: 0s - loss: 1.3758 - accuracy: 0.5107 3200/3595 [=========================>....] - ETA: 0s - loss: 1.3707 - accuracy: 0.5109 3328/3595 [==========================>...] - ETA: 0s - loss: 1.3703 - accuracy: 0.5114 3456/3595 [===========================>..] - ETA: 0s - loss: 1.3704 - accuracy: 0.5136 3584/3595 [============================>.] - ETA: 0s - loss: 1.3681 - accuracy: 0.5137 3595/3595 [==============================] - 2s 552us/sample - loss: 1.3667 - accuracy: 0.5143 - val_loss: 1.3018 - val_accuracy: 0.5495 Epoch 8/28 32/3595 [..............................] - ETA: 1s - loss: 1.0503 - accuracy: 0.6250 160/3595 [>.............................] - ETA: 1s - loss: 1.1770 - accuracy: 0.5625 288/3595 [=>............................] - ETA: 1s - loss: 1.2397 - accuracy: 0.5694 416/3595 [==>...........................] - ETA: 1s - loss: 1.2430 - accuracy: 0.5553 512/3595 [===>..........................] - ETA: 1s - loss: 1.2423 - accuracy: 0.5586 640/3595 [====>.........................] - ETA: 1s - loss: 1.2757 - accuracy: 0.5453 768/3595 [=====>........................] - ETA: 1s - loss: 1.2896 - accuracy: 0.5299 896/3595 [======>.......................] - ETA: 1s - loss: 1.2807 - accuracy: 0.5379 1024/3595 [=======>......................] - ETA: 1s - loss: 1.2689 - accuracy: 0.5400 1152/3595 [========>.....................] - ETA: 1s - loss: 1.2541 - accuracy: 0.5477 1280/3595 [=========>....................] - ETA: 1s - loss: 1.2568 - accuracy: 0.5531 1408/3595 [==========>...................] - ETA: 1s - loss: 1.2747 - accuracy: 0.5511 1536/3595 [===========>..................] - ETA: 1s - loss: 1.2802 - accuracy: 0.5462 1664/3595 [============>.................] - ETA: 0s - loss: 1.2839 - accuracy: 0.5463 1760/3595 [=============>................] - ETA: 0s - loss: 1.2812 - accuracy: 0.5455 1888/3595 [==============>...............] - ETA: 0s - loss: 1.2787 - accuracy: 0.5434 2016/3595 [===============>..............] - ETA: 0s - loss: 1.2781 - accuracy: 0.5441 2144/3595 [================>.............] - ETA: 0s - loss: 1.2820 - accuracy: 0.5448 2272/3595 [=================>............] - ETA: 0s - loss: 1.2856 - accuracy: 0.5423 2400/3595 [===================>..........] - ETA: 0s - loss: 1.2804 - accuracy: 0.5446 2528/3595 [====================>.........] - ETA: 0s - loss: 1.2754 - accuracy: 0.5467 2656/3595 [=====================>........] - ETA: 0s - loss: 1.2754 - accuracy: 0.5463 2784/3595 [======================>.......] - ETA: 0s - loss: 1.2677 - accuracy: 0.5485 2912/3595 [=======================>......] - ETA: 0s - loss: 1.2666 - accuracy: 0.5481 3040/3595 [========================>.....] - ETA: 0s - loss: 1.2668 - accuracy: 0.5461 3168/3595 [=========================>....] - ETA: 0s - loss: 1.2661 - accuracy: 0.5467 3296/3595 [==========================>...] - ETA: 0s - loss: 1.2662 - accuracy: 0.5473 3392/3595 [===========================>..] - ETA: 0s - loss: 1.2576 - accuracy: 0.5516 3520/3595 [============================>.] - ETA: 0s - loss: 1.2561 - accuracy: 0.5523 3595/3595 [==============================] - 2s 531us/sample - loss: 1.2564 - accuracy: 0.5516 - val_loss: 1.2654 - val_accuracy: 0.5451 Epoch 9/28 32/3595 [..............................] - ETA: 1s - loss: 1.1013 - accuracy: 0.5312 128/3595 [>.............................] - ETA: 2s - loss: 1.1274 - accuracy: 0.5469 256/3595 [=>............................] - ETA: 1s - loss: 1.2150 - accuracy: 0.5508 384/3595 [==>...........................] - ETA: 1s - loss: 1.1846 - accuracy: 0.5573 512/3595 [===>..........................] - ETA: 1s - loss: 1.1866 - accuracy: 0.5605 640/3595 [====>.........................] - ETA: 1s - loss: 1.1390 - accuracy: 0.5891 736/3595 [=====>........................] - ETA: 1s - loss: 1.1287 - accuracy: 0.5897 864/3595 [======>.......................] - ETA: 1s - loss: 1.1611 - accuracy: 0.5822 992/3595 [=======>......................] - ETA: 1s - loss: 1.1526 - accuracy: 0.5837 1120/3595 [========>.....................] - ETA: 1s - loss: 1.1722 - accuracy: 0.5839 1248/3595 [=========>....................] - ETA: 1s - loss: 1.1708 - accuracy: 0.5833 1376/3595 [==========>...................] - ETA: 1s - loss: 1.1742 - accuracy: 0.5807 1504/3595 [===========>..................] - ETA: 1s - loss: 1.1847 - accuracy: 0.5785 1632/3595 [============>.................] - ETA: 1s - loss: 1.1923 - accuracy: 0.5717 1760/3595 [=============>................] - ETA: 0s - loss: 1.1997 - accuracy: 0.5659 1888/3595 [==============>...............] - ETA: 0s - loss: 1.2005 - accuracy: 0.5667 2016/3595 [===============>..............] - ETA: 0s - loss: 1.2027 - accuracy: 0.5670 2112/3595 [================>.............] - ETA: 0s - loss: 1.2117 - accuracy: 0.5630 2272/3595 [=================>............] - ETA: 0s - loss: 1.2163 - accuracy: 0.5647 2400/3595 [===================>..........] - ETA: 0s - loss: 1.2210 - accuracy: 0.5638 2528/3595 [====================>.........] - ETA: 0s - loss: 1.2198 - accuracy: 0.5688 2656/3595 [=====================>........] - ETA: 0s - loss: 1.2189 - accuracy: 0.5685 2784/3595 [======================>.......] - ETA: 0s - loss: 1.2187 - accuracy: 0.5675 2880/3595 [=======================>......] - ETA: 0s - loss: 1.2220 - accuracy: 0.5653 3008/3595 [========================>.....] - ETA: 0s - loss: 1.2285 - accuracy: 0.5635 3104/3595 [========================>.....] - ETA: 0s - loss: 1.2289 - accuracy: 0.5631 3200/3595 [=========================>....] - ETA: 0s - loss: 1.2262 - accuracy: 0.5641 3296/3595 [==========================>...] - ETA: 0s - loss: 1.2284 - accuracy: 0.5622 3424/3595 [===========================>..] - ETA: 0s - loss: 1.2237 - accuracy: 0.5622 3552/3595 [============================>.] - ETA: 0s - loss: 1.2247 - accuracy: 0.5625 3595/3595 [==============================] - 2s 561us/sample - loss: 1.2205 - accuracy: 0.5638 - val_loss: 1.2472 - val_accuracy: 0.5595 Epoch 10/28 32/3595 [..............................] - ETA: 1s - loss: 1.4746 - accuracy: 0.3750 160/3595 [>.............................] - ETA: 1s - loss: 1.2281 - accuracy: 0.5375 288/3595 [=>............................] - ETA: 1s - loss: 1.1737 - accuracy: 0.5590 384/3595 [==>...........................] - ETA: 1s - loss: 1.2227 - accuracy: 0.5547 512/3595 [===>..........................] - ETA: 1s - loss: 1.1930 - accuracy: 0.5801 640/3595 [====>.........................] - ETA: 1s - loss: 1.1790 - accuracy: 0.5828 768/3595 [=====>........................] - ETA: 1s - loss: 1.1700 - accuracy: 0.5938 896/3595 [======>.......................] - ETA: 1s - loss: 1.1742 - accuracy: 0.5926 1024/3595 [=======>......................] - ETA: 1s - loss: 1.1787 - accuracy: 0.5850 1120/3595 [========>.....................] - ETA: 1s - loss: 1.1709 - accuracy: 0.5911 1248/3595 [=========>....................] - ETA: 1s - loss: 1.1771 - accuracy: 0.5913 1376/3595 [==========>...................] - ETA: 1s - loss: 1.1802 - accuracy: 0.5879 1504/3595 [===========>..................] - ETA: 1s - loss: 1.1996 - accuracy: 0.5864 1632/3595 [============>.................] - ETA: 0s - loss: 1.1936 - accuracy: 0.5876 1760/3595 [=============>................] - ETA: 0s - loss: 1.1966 - accuracy: 0.5864 1888/3595 [==============>...............] - ETA: 0s - loss: 1.1991 - accuracy: 0.5847 2016/3595 [===============>..............] - ETA: 0s - loss: 1.1896 - accuracy: 0.5898 2144/3595 [================>.............] - ETA: 0s - loss: 1.1899 - accuracy: 0.5905 2272/3595 [=================>............] - ETA: 0s - loss: 1.1875 - accuracy: 0.5902 2400/3595 [===================>..........] - ETA: 0s - loss: 1.1890 - accuracy: 0.5913 2528/3595 [====================>.........] - ETA: 0s - loss: 1.1821 - accuracy: 0.5926 2656/3595 [=====================>........] - ETA: 0s - loss: 1.1784 - accuracy: 0.5919 2784/3595 [======================>.......] - ETA: 0s - loss: 1.1766 - accuracy: 0.5909 2912/3595 [=======================>......] - ETA: 0s - loss: 1.1786 - accuracy: 0.5889 3040/3595 [========================>.....] - ETA: 0s - loss: 1.1833 - accuracy: 0.5878 3168/3595 [=========================>....] - ETA: 0s - loss: 1.1811 - accuracy: 0.5871 3296/3595 [==========================>...] - ETA: 0s - loss: 1.1810 - accuracy: 0.5853 3424/3595 [===========================>..] - ETA: 0s - loss: 1.1784 - accuracy: 0.5850 3552/3595 [============================>.] - ETA: 0s - loss: 1.1750 - accuracy: 0.5861 3595/3595 [==============================] - 2s 539us/sample - loss: 1.1721 - accuracy: 0.5875 - val_loss: 1.1947 - val_accuracy: 0.5706 Epoch 11/28 32/3595 [..............................] - ETA: 1s - loss: 1.3050 - accuracy: 0.5625 160/3595 [>.............................] - ETA: 1s - loss: 1.1524 - accuracy: 0.5750 288/3595 [=>............................] - ETA: 1s - loss: 1.1019 - accuracy: 0.5868 384/3595 [==>...........................] - ETA: 1s - loss: 1.0907 - accuracy: 0.5964 512/3595 [===>..........................] - ETA: 1s - loss: 1.0950 - accuracy: 0.6016 640/3595 [====>.........................] - ETA: 1s - loss: 1.1460 - accuracy: 0.5781 768/3595 [=====>........................] - ETA: 1s - loss: 1.1263 - accuracy: 0.5781 896/3595 [======>.......................] - ETA: 1s - loss: 1.1369 - accuracy: 0.5781 1024/3595 [=======>......................] - ETA: 1s - loss: 1.1617 - accuracy: 0.5781 1152/3595 [========>.....................] - ETA: 1s - loss: 1.1451 - accuracy: 0.5833 1280/3595 [=========>....................] - ETA: 1s - loss: 1.1403 - accuracy: 0.5859 1408/3595 [==========>...................] - ETA: 1s - loss: 1.1169 - accuracy: 0.5945 1536/3595 [===========>..................] - ETA: 1s - loss: 1.1184 - accuracy: 0.5983 1632/3595 [============>.................] - ETA: 1s - loss: 1.1287 - accuracy: 0.5907 1760/3595 [=============>................] - ETA: 0s - loss: 1.1358 - accuracy: 0.5858 1888/3595 [==============>...............] - ETA: 0s - loss: 1.1334 - accuracy: 0.5869 2016/3595 [===============>..............] - ETA: 0s - loss: 1.1376 - accuracy: 0.5858 2144/3595 [================>.............] - ETA: 0s - loss: 1.1335 - accuracy: 0.5900 2240/3595 [=================>............] - ETA: 0s - loss: 1.1259 - accuracy: 0.5942 2336/3595 [==================>...........] - ETA: 0s - loss: 1.1303 - accuracy: 0.5933 2464/3595 [===================>..........] - ETA: 0s - loss: 1.1382 - accuracy: 0.5905 2592/3595 [====================>.........] - ETA: 0s - loss: 1.1351 - accuracy: 0.5887 2720/3595 [=====================>........] - ETA: 0s - loss: 1.1403 - accuracy: 0.5875 2848/3595 [======================>.......] - ETA: 0s - loss: 1.1374 - accuracy: 0.5913 2944/3595 [=======================>......] - ETA: 0s - loss: 1.1407 - accuracy: 0.5887 3072/3595 [========================>.....] - ETA: 0s - loss: 1.1421 - accuracy: 0.5895 3200/3595 [=========================>....] - ETA: 0s - loss: 1.1400 - accuracy: 0.5900 3328/3595 [==========================>...] - ETA: 0s - loss: 1.1414 - accuracy: 0.5907 3456/3595 [===========================>..] - ETA: 0s - loss: 1.1361 - accuracy: 0.5932 3552/3595 [============================>.] - ETA: 0s - loss: 1.1304 - accuracy: 0.5954 3595/3595 [==============================] - 2s 550us/sample - loss: 1.1357 - accuracy: 0.5930 - val_loss: 1.1671 - val_accuracy: 0.5862 Epoch 12/28 32/3595 [..............................] - ETA: 1s - loss: 1.1483 - accuracy: 0.6250 160/3595 [>.............................] - ETA: 1s - loss: 1.1206 - accuracy: 0.6187 288/3595 [=>............................] - ETA: 1s - loss: 1.1342 - accuracy: 0.6181 384/3595 [==>...........................] - ETA: 1s - loss: 1.1552 - accuracy: 0.6120 512/3595 [===>..........................] - ETA: 1s - loss: 1.1178 - accuracy: 0.6211 640/3595 [====>.........................] - ETA: 1s - loss: 1.0797 - accuracy: 0.6266 736/3595 [=====>........................] - ETA: 1s - loss: 1.0688 - accuracy: 0.6264 864/3595 [======>.......................] - ETA: 1s - loss: 1.0861 - accuracy: 0.6134 992/3595 [=======>......................] - ETA: 1s - loss: 1.0889 - accuracy: 0.6139 1120/3595 [========>.....................] - ETA: 1s - loss: 1.1000 - accuracy: 0.6116 1248/3595 [=========>....................] - ETA: 1s - loss: 1.0829 - accuracy: 0.6186 1344/3595 [==========>...................] - ETA: 1s - loss: 1.0863 - accuracy: 0.6176 1472/3595 [===========>..................] - ETA: 1s - loss: 1.0881 - accuracy: 0.6128 1600/3595 [============>.................] - ETA: 1s - loss: 1.0923 - accuracy: 0.6094 1728/3595 [=============>................] - ETA: 0s - loss: 1.0909 - accuracy: 0.6105 1856/3595 [==============>...............] - ETA: 0s - loss: 1.0935 - accuracy: 0.6115 1952/3595 [===============>..............] - ETA: 0s - loss: 1.0840 - accuracy: 0.6194 2048/3595 [================>.............] - ETA: 0s - loss: 1.0781 - accuracy: 0.6221 2144/3595 [================>.............] - ETA: 0s - loss: 1.0797 - accuracy: 0.6199 2272/3595 [=================>............] - ETA: 0s - loss: 1.0766 - accuracy: 0.6237 2368/3595 [==================>...........] - ETA: 0s - loss: 1.0798 - accuracy: 0.6229 2496/3595 [===================>..........] - ETA: 0s - loss: 1.0787 - accuracy: 0.6222 2624/3595 [====================>.........] - ETA: 0s - loss: 1.0726 - accuracy: 0.6235 2752/3595 [=====================>........] - ETA: 0s - loss: 1.0797 - accuracy: 0.6185 2880/3595 [=======================>......] - ETA: 0s - loss: 1.0721 - accuracy: 0.6229 2976/3595 [=======================>......] - ETA: 0s - loss: 1.0699 - accuracy: 0.6233 3104/3595 [========================>.....] - ETA: 0s - loss: 1.0677 - accuracy: 0.6250 3232/3595 [=========================>....] - ETA: 0s - loss: 1.0678 - accuracy: 0.6244 3360/3595 [===========================>..] - ETA: 0s - loss: 1.0741 - accuracy: 0.6211 3488/3595 [============================>.] - ETA: 0s - loss: 1.0747 - accuracy: 0.6221 3595/3595 [==============================] - 2s 555us/sample - loss: 1.0733 - accuracy: 0.6206 - val_loss: 1.1429 - val_accuracy: 0.5996 Epoch 13/28 32/3595 [..............................] - ETA: 1s - loss: 0.9492 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 1s - loss: 0.9749 - accuracy: 0.6687 288/3595 [=>............................] - ETA: 1s - loss: 0.9952 - accuracy: 0.6632 384/3595 [==>...........................] - ETA: 1s - loss: 0.9967 - accuracy: 0.6615 512/3595 [===>..........................] - ETA: 1s - loss: 1.0113 - accuracy: 0.6562 640/3595 [====>.........................] - ETA: 1s - loss: 1.0252 - accuracy: 0.6531 768/3595 [=====>........................] - ETA: 1s - loss: 1.0195 - accuracy: 0.6445 896/3595 [======>.......................] - ETA: 1s - loss: 1.0022 - accuracy: 0.6518 1024/3595 [=======>......................] - ETA: 1s - loss: 1.0042 - accuracy: 0.6533 1120/3595 [========>.....................] - ETA: 1s - loss: 1.0197 - accuracy: 0.6491 1248/3595 [=========>....................] - ETA: 1s - loss: 1.0214 - accuracy: 0.6538 1376/3595 [==========>...................] - ETA: 1s - loss: 1.0239 - accuracy: 0.6519 1504/3595 [===========>..................] - ETA: 1s - loss: 1.0348 - accuracy: 0.6496 1632/3595 [============>.................] - ETA: 0s - loss: 1.0353 - accuracy: 0.6501 1728/3595 [=============>................] - ETA: 0s - loss: 1.0321 - accuracy: 0.6516 1856/3595 [==============>...............] - ETA: 0s - loss: 1.0322 - accuracy: 0.6514 1984/3595 [===============>..............] - ETA: 0s - loss: 1.0252 - accuracy: 0.6562 2112/3595 [================>.............] - ETA: 0s - loss: 1.0184 - accuracy: 0.6562 2240/3595 [=================>............] - ETA: 0s - loss: 1.0227 - accuracy: 0.6522 2336/3595 [==================>...........] - ETA: 0s - loss: 1.0276 - accuracy: 0.6477 2464/3595 [===================>..........] - ETA: 0s - loss: 1.0208 - accuracy: 0.6498 2592/3595 [====================>.........] - ETA: 0s - loss: 1.0222 - accuracy: 0.6481 2720/3595 [=====================>........] - ETA: 0s - loss: 1.0232 - accuracy: 0.6474 2816/3595 [======================>.......] - ETA: 0s - loss: 1.0283 - accuracy: 0.6452 2944/3595 [=======================>......] - ETA: 0s - loss: 1.0326 - accuracy: 0.6430 3072/3595 [========================>.....] - ETA: 0s - loss: 1.0370 - accuracy: 0.6396 3200/3595 [=========================>....] - ETA: 0s - loss: 1.0391 - accuracy: 0.6369 3328/3595 [==========================>...] - ETA: 0s - loss: 1.0420 - accuracy: 0.6337 3424/3595 [===========================>..] - ETA: 0s - loss: 1.0383 - accuracy: 0.6349 3552/3595 [============================>.] - ETA: 0s - loss: 1.0405 - accuracy: 0.6326 3595/3595 [==============================] - 2s 548us/sample - loss: 1.0389 - accuracy: 0.6337 - val_loss: 1.1359 - val_accuracy: 0.5862 Epoch 14/28 32/3595 [..............................] - ETA: 1s - loss: 0.8459 - accuracy: 0.6562 160/3595 [>.............................] - ETA: 1s - loss: 1.0861 - accuracy: 0.6187 288/3595 [=>............................] - ETA: 1s - loss: 1.1178 - accuracy: 0.6007 416/3595 [==>...........................] - ETA: 1s - loss: 1.1040 - accuracy: 0.6082 544/3595 [===>..........................] - ETA: 1s - loss: 1.0641 - accuracy: 0.6195 672/3595 [====>.........................] - ETA: 1s - loss: 1.0621 - accuracy: 0.6235 800/3595 [=====>........................] - ETA: 1s - loss: 1.0378 - accuracy: 0.6275 928/3595 [======>.......................] - ETA: 1s - loss: 1.0318 - accuracy: 0.6272 1056/3595 [=======>......................] - ETA: 1s - loss: 1.0086 - accuracy: 0.6392 1184/3595 [========>.....................] - ETA: 1s - loss: 1.0162 - accuracy: 0.6385 1312/3595 [=========>....................] - ETA: 1s - loss: 1.0341 - accuracy: 0.6311 1440/3595 [===========>..................] - ETA: 1s - loss: 1.0350 - accuracy: 0.6313 1568/3595 [============>.................] - ETA: 1s - loss: 1.0238 - accuracy: 0.6365 1664/3595 [============>.................] - ETA: 0s - loss: 1.0112 - accuracy: 0.6424 1792/3595 [=============>................] - ETA: 0s - loss: 1.0244 - accuracy: 0.6362 1920/3595 [===============>..............] - ETA: 0s - loss: 1.0201 - accuracy: 0.6380 2048/3595 [================>.............] - ETA: 0s - loss: 1.0252 - accuracy: 0.6304 2176/3595 [=================>............] - ETA: 0s - loss: 1.0246 - accuracy: 0.6337 2304/3595 [==================>...........] - ETA: 0s - loss: 1.0250 - accuracy: 0.6328 2432/3595 [===================>..........] - ETA: 0s - loss: 1.0140 - accuracy: 0.6377 2560/3595 [====================>.........] - ETA: 0s - loss: 1.0096 - accuracy: 0.6398 2688/3595 [=====================>........] - ETA: 0s - loss: 1.0064 - accuracy: 0.6410 2816/3595 [======================>.......] - ETA: 0s - loss: 1.0022 - accuracy: 0.6428 2944/3595 [=======================>......] - ETA: 0s - loss: 1.0017 - accuracy: 0.6433 3072/3595 [========================>.....] - ETA: 0s - loss: 0.9970 - accuracy: 0.6468 3200/3595 [=========================>....] - ETA: 0s - loss: 0.9984 - accuracy: 0.6466 3328/3595 [==========================>...] - ETA: 0s - loss: 0.9963 - accuracy: 0.6481 3456/3595 [===========================>..] - ETA: 0s - loss: 0.9958 - accuracy: 0.6467 3584/3595 [============================>.] - ETA: 0s - loss: 0.9978 - accuracy: 0.6440 3595/3595 [==============================] - 2s 530us/sample - loss: 0.9989 - accuracy: 0.6437 - val_loss: 1.1184 - val_accuracy: 0.6140 Epoch 15/28 32/3595 [..............................] - ETA: 1s - loss: 0.7184 - accuracy: 0.7812 128/3595 [>.............................] - ETA: 2s - loss: 0.8233 - accuracy: 0.6875 256/3595 [=>............................] - ETA: 1s - loss: 0.7939 - accuracy: 0.7227 384/3595 [==>...........................] - ETA: 1s - loss: 0.8361 - accuracy: 0.7135 512/3595 [===>..........................] - ETA: 1s - loss: 0.8588 - accuracy: 0.6992 640/3595 [====>.........................] - ETA: 1s - loss: 0.8923 - accuracy: 0.6828 768/3595 [=====>........................] - ETA: 1s - loss: 0.9165 - accuracy: 0.6836 864/3595 [======>.......................] - ETA: 1s - loss: 0.9256 - accuracy: 0.6829 960/3595 [=======>......................] - ETA: 1s - loss: 0.9373 - accuracy: 0.6792 1056/3595 [=======>......................] - ETA: 1s - loss: 0.9386 - accuracy: 0.6799 1184/3595 [========>.....................] - ETA: 1s - loss: 0.9360 - accuracy: 0.6807 1312/3595 [=========>....................] - ETA: 1s - loss: 0.9326 - accuracy: 0.6806 1440/3595 [===========>..................] - ETA: 1s - loss: 0.9400 - accuracy: 0.6736 1536/3595 [===========>..................] - ETA: 1s - loss: 0.9370 - accuracy: 0.6777 1664/3595 [============>.................] - ETA: 1s - loss: 0.9485 - accuracy: 0.6737 1792/3595 [=============>................] - ETA: 0s - loss: 0.9485 - accuracy: 0.6713 1920/3595 [===============>..............] - ETA: 0s - loss: 0.9500 - accuracy: 0.6740 2048/3595 [================>.............] - ETA: 0s - loss: 0.9577 - accuracy: 0.6733 2176/3595 [=================>............] - ETA: 0s - loss: 0.9635 - accuracy: 0.6700 2304/3595 [==================>...........] - ETA: 0s - loss: 0.9704 - accuracy: 0.6636 2432/3595 [===================>..........] - ETA: 0s - loss: 0.9762 - accuracy: 0.6632 2560/3595 [====================>.........] - ETA: 0s - loss: 0.9812 - accuracy: 0.6633 2688/3595 [=====================>........] - ETA: 0s - loss: 0.9760 - accuracy: 0.6637 2816/3595 [======================>.......] - ETA: 0s - loss: 0.9799 - accuracy: 0.6623 2944/3595 [=======================>......] - ETA: 0s - loss: 0.9813 - accuracy: 0.6610 3072/3595 [========================>.....] - ETA: 0s - loss: 0.9816 - accuracy: 0.6611 3200/3595 [=========================>....] - ETA: 0s - loss: 0.9780 - accuracy: 0.6622 3328/3595 [==========================>...] - ETA: 0s - loss: 0.9760 - accuracy: 0.6629 3456/3595 [===========================>..] - ETA: 0s - loss: 0.9715 - accuracy: 0.6646 3584/3595 [============================>.] - ETA: 0s - loss: 0.9688 - accuracy: 0.6655 3595/3595 [==============================] - 2s 553us/sample - loss: 0.9671 - accuracy: 0.6662 - val_loss: 1.0963 - val_accuracy: 0.6162 Epoch 16/28 32/3595 [..............................] - ETA: 1s - loss: 0.7559 - accuracy: 0.7188 160/3595 [>.............................] - ETA: 1s - loss: 0.8167 - accuracy: 0.7125 256/3595 [=>............................] - ETA: 1s - loss: 0.8488 - accuracy: 0.7148 384/3595 [==>...........................] - ETA: 1s - loss: 0.8498 - accuracy: 0.7083 512/3595 [===>..........................] - ETA: 1s - loss: 0.8781 - accuracy: 0.6914 608/3595 [====>.........................] - ETA: 1s - loss: 0.9021 - accuracy: 0.6776 736/3595 [=====>........................] - ETA: 1s - loss: 0.9359 - accuracy: 0.6712 864/3595 [======>.......................] - ETA: 1s - loss: 0.9295 - accuracy: 0.6771 992/3595 [=======>......................] - ETA: 1s - loss: 0.9126 - accuracy: 0.6784 1088/3595 [========>.....................] - ETA: 1s - loss: 0.9157 - accuracy: 0.6746 1216/3595 [=========>....................] - ETA: 1s - loss: 0.9100 - accuracy: 0.6768 1344/3595 [==========>...................] - ETA: 1s - loss: 0.9049 - accuracy: 0.6756 1472/3595 [===========>..................] - ETA: 1s - loss: 0.8972 - accuracy: 0.6766 1600/3595 [============>.................] - ETA: 1s - loss: 0.8977 - accuracy: 0.6750 1728/3595 [=============>................] - ETA: 0s - loss: 0.9005 - accuracy: 0.6771 1856/3595 [==============>...............] - ETA: 0s - loss: 0.9033 - accuracy: 0.6794 1984/3595 [===============>..............] - ETA: 0s - loss: 0.8984 - accuracy: 0.6825 2080/3595 [================>.............] - ETA: 0s - loss: 0.8989 - accuracy: 0.6812 2208/3595 [=================>............] - ETA: 0s - loss: 0.9051 - accuracy: 0.6807 2336/3595 [==================>...........] - ETA: 0s - loss: 0.9129 - accuracy: 0.6785 2464/3595 [===================>..........] - ETA: 0s - loss: 0.9084 - accuracy: 0.6822 2592/3595 [====================>.........] - ETA: 0s - loss: 0.9064 - accuracy: 0.6806 2720/3595 [=====================>........] - ETA: 0s - loss: 0.9151 - accuracy: 0.6779 2848/3595 [======================>.......] - ETA: 0s - loss: 0.9150 - accuracy: 0.6773 2976/3595 [=======================>......] - ETA: 0s - loss: 0.9176 - accuracy: 0.6771 3104/3595 [========================>.....] - ETA: 0s - loss: 0.9173 - accuracy: 0.6765 3232/3595 [=========================>....] - ETA: 0s - loss: 0.9186 - accuracy: 0.6764 3360/3595 [===========================>..] - ETA: 0s - loss: 0.9183 - accuracy: 0.6771 3488/3595 [============================>.] - ETA: 0s - loss: 0.9228 - accuracy: 0.6743 3595/3595 [==============================] - 2s 540us/sample - loss: 0.9178 - accuracy: 0.6762 - val_loss: 1.0643 - val_accuracy: 0.6174 Epoch 17/28 32/3595 [..............................] - ETA: 1s - loss: 0.8977 - accuracy: 0.6562 160/3595 [>.............................] - ETA: 1s - loss: 0.8371 - accuracy: 0.6812 256/3595 [=>............................] - ETA: 1s - loss: 0.8434 - accuracy: 0.6797 384/3595 [==>...........................] - ETA: 1s - loss: 0.8642 - accuracy: 0.6849 512/3595 [===>..........................] - ETA: 1s - loss: 0.8687 - accuracy: 0.6797 640/3595 [====>.........................] - ETA: 1s - loss: 0.8508 - accuracy: 0.6859 736/3595 [=====>........................] - ETA: 1s - loss: 0.8743 - accuracy: 0.6943 864/3595 [======>.......................] - ETA: 1s - loss: 0.8768 - accuracy: 0.6852 992/3595 [=======>......................] - ETA: 1s - loss: 0.8936 - accuracy: 0.6754 1120/3595 [========>.....................] - ETA: 1s - loss: 0.8864 - accuracy: 0.6812 1216/3595 [=========>....................] - ETA: 1s - loss: 0.8779 - accuracy: 0.6883 1344/3595 [==========>...................] - ETA: 1s - loss: 0.8654 - accuracy: 0.6912 1472/3595 [===========>..................] - ETA: 1s - loss: 0.8759 - accuracy: 0.6868 1600/3595 [============>.................] - ETA: 1s - loss: 0.8681 - accuracy: 0.6906 1728/3595 [=============>................] - ETA: 0s - loss: 0.8702 - accuracy: 0.6892 1856/3595 [==============>...............] - ETA: 0s - loss: 0.8777 - accuracy: 0.6837 1984/3595 [===============>..............] - ETA: 0s - loss: 0.8797 - accuracy: 0.6820 2112/3595 [================>.............] - ETA: 0s - loss: 0.8831 - accuracy: 0.6799 2240/3595 [=================>............] - ETA: 0s - loss: 0.8870 - accuracy: 0.6812 2368/3595 [==================>...........] - ETA: 0s - loss: 0.8819 - accuracy: 0.6845 2496/3595 [===================>..........] - ETA: 0s - loss: 0.8839 - accuracy: 0.6831 2592/3595 [====================>.........] - ETA: 0s - loss: 0.8842 - accuracy: 0.6848 2720/3595 [=====================>........] - ETA: 0s - loss: 0.8809 - accuracy: 0.6864 2848/3595 [======================>.......] - ETA: 0s - loss: 0.8917 - accuracy: 0.6836 2976/3595 [=======================>......] - ETA: 0s - loss: 0.8934 - accuracy: 0.6818 3104/3595 [========================>.....] - ETA: 0s - loss: 0.8897 - accuracy: 0.6846 3200/3595 [=========================>....] - ETA: 0s - loss: 0.8903 - accuracy: 0.6837 3328/3595 [==========================>...] - ETA: 0s - loss: 0.8890 - accuracy: 0.6833 3456/3595 [===========================>..] - ETA: 0s - loss: 0.8917 - accuracy: 0.6814 3584/3595 [============================>.] - ETA: 0s - loss: 0.8998 - accuracy: 0.6794 3595/3595 [==============================] - 2s 557us/sample - loss: 0.8994 - accuracy: 0.6796 - val_loss: 1.0583 - val_accuracy: 0.6218 Epoch 18/28 32/3595 [..............................] - ETA: 3s - loss: 0.6707 - accuracy: 0.7500 160/3595 [>.............................] - ETA: 2s - loss: 0.8512 - accuracy: 0.6875 288/3595 [=>............................] - ETA: 2s - loss: 0.8783 - accuracy: 0.6806 416/3595 [==>...........................] - ETA: 1s - loss: 0.8699 - accuracy: 0.6947 544/3595 [===>..........................] - ETA: 1s - loss: 0.8174 - accuracy: 0.7151 672/3595 [====>.........................] - ETA: 1s - loss: 0.8241 - accuracy: 0.7098 800/3595 [=====>........................] - ETA: 1s - loss: 0.8418 - accuracy: 0.7100 928/3595 [======>.......................] - ETA: 1s - loss: 0.8480 - accuracy: 0.7091 1056/3595 [=======>......................] - ETA: 1s - loss: 0.8427 - accuracy: 0.7093 1152/3595 [========>.....................] - ETA: 1s - loss: 0.8492 - accuracy: 0.7083 1280/3595 [=========>....................] - ETA: 1s - loss: 0.8441 - accuracy: 0.7047 1408/3595 [==========>...................] - ETA: 1s - loss: 0.8380 - accuracy: 0.7081 1536/3595 [===========>..................] - ETA: 1s - loss: 0.8379 - accuracy: 0.7083 1664/3595 [============>.................] - ETA: 1s - loss: 0.8432 - accuracy: 0.7067 1792/3595 [=============>................] - ETA: 0s - loss: 0.8380 - accuracy: 0.7076 1920/3595 [===============>..............] - ETA: 0s - loss: 0.8388 - accuracy: 0.7083 2048/3595 [================>.............] - ETA: 0s - loss: 0.8320 - accuracy: 0.7124 2176/3595 [=================>............] - ETA: 0s - loss: 0.8317 - accuracy: 0.7128 2304/3595 [==================>...........] - ETA: 0s - loss: 0.8325 - accuracy: 0.7131 2432/3595 [===================>..........] - ETA: 0s - loss: 0.8347 - accuracy: 0.7126 2560/3595 [====================>.........] - ETA: 0s - loss: 0.8377 - accuracy: 0.7145 2688/3595 [=====================>........] - ETA: 0s - loss: 0.8379 - accuracy: 0.7128 2848/3595 [======================>.......] - ETA: 0s - loss: 0.8382 - accuracy: 0.7142 2976/3595 [=======================>......] - ETA: 0s - loss: 0.8417 - accuracy: 0.7110 3104/3595 [========================>.....] - ETA: 0s - loss: 0.8448 - accuracy: 0.7097 3232/3595 [=========================>....] - ETA: 0s - loss: 0.8462 - accuracy: 0.7073 3360/3595 [===========================>..] - ETA: 0s - loss: 0.8440 - accuracy: 0.7086 3488/3595 [============================>.] - ETA: 0s - loss: 0.8476 - accuracy: 0.7079 3595/3595 [==============================] - 2s 540us/sample - loss: 0.8517 - accuracy: 0.7063 - val_loss: 1.0563 - val_accuracy: 0.6307 Epoch 19/28 32/3595 [..............................] - ETA: 1s - loss: 0.8190 - accuracy: 0.6875 128/3595 [>.............................] - ETA: 2s - loss: 0.8013 - accuracy: 0.7031 256/3595 [=>............................] - ETA: 1s - loss: 0.8556 - accuracy: 0.6914 384/3595 [==>...........................] - ETA: 1s - loss: 0.8885 - accuracy: 0.6901 512/3595 [===>..........................] - ETA: 1s - loss: 0.8449 - accuracy: 0.6895 640/3595 [====>.........................] - ETA: 1s - loss: 0.8710 - accuracy: 0.6938 768/3595 [=====>........................] - ETA: 1s - loss: 0.8742 - accuracy: 0.6927 864/3595 [======>.......................] - ETA: 1s - loss: 0.8846 - accuracy: 0.6887 992/3595 [=======>......................] - ETA: 1s - loss: 0.8761 - accuracy: 0.6966 1120/3595 [========>.....................] - ETA: 1s - loss: 0.8686 - accuracy: 0.7000 1248/3595 [=========>....................] - ETA: 1s - loss: 0.8591 - accuracy: 0.7035 1376/3595 [==========>...................] - ETA: 1s - loss: 0.8486 - accuracy: 0.7071 1504/3595 [===========>..................] - ETA: 1s - loss: 0.8484 - accuracy: 0.7101 1600/3595 [============>.................] - ETA: 1s - loss: 0.8428 - accuracy: 0.7138 1728/3595 [=============>................] - ETA: 0s - loss: 0.8385 - accuracy: 0.7170 1856/3595 [==============>...............] - ETA: 0s - loss: 0.8478 - accuracy: 0.7134 1984/3595 [===============>..............] - ETA: 0s - loss: 0.8435 - accuracy: 0.7137 2112/3595 [================>.............] - ETA: 0s - loss: 0.8496 - accuracy: 0.7083 2208/3595 [=================>............] - ETA: 0s - loss: 0.8493 - accuracy: 0.7074 2336/3595 [==================>...........] - ETA: 0s - loss: 0.8502 - accuracy: 0.7080 2464/3595 [===================>..........] - ETA: 0s - loss: 0.8593 - accuracy: 0.7054 2592/3595 [====================>.........] - ETA: 0s - loss: 0.8537 - accuracy: 0.7068 2720/3595 [=====================>........] - ETA: 0s - loss: 0.8543 - accuracy: 0.7077 2848/3595 [======================>.......] - ETA: 0s - loss: 0.8494 - accuracy: 0.7086 2976/3595 [=======================>......] - ETA: 0s - loss: 0.8476 - accuracy: 0.7093 3104/3595 [========================>.....] - ETA: 0s - loss: 0.8497 - accuracy: 0.7104 3232/3595 [=========================>....] - ETA: 0s - loss: 0.8466 - accuracy: 0.7107 3328/3595 [==========================>...] - ETA: 0s - loss: 0.8466 - accuracy: 0.7106 3456/3595 [===========================>..] - ETA: 0s - loss: 0.8486 - accuracy: 0.7106 3584/3595 [============================>.] - ETA: 0s - loss: 0.8473 - accuracy: 0.7121 3595/3595 [==============================] - 2s 549us/sample - loss: 0.8472 - accuracy: 0.7124 - val_loss: 1.0401 - val_accuracy: 0.6240 Epoch 20/28 32/3595 [..............................] - ETA: 1s - loss: 0.9186 - accuracy: 0.7500 160/3595 [>.............................] - ETA: 1s - loss: 0.8054 - accuracy: 0.7250 288/3595 [=>............................] - ETA: 1s - loss: 0.7982 - accuracy: 0.7083 416/3595 [==>...........................] - ETA: 1s - loss: 0.8046 - accuracy: 0.7043 544/3595 [===>..........................] - ETA: 1s - loss: 0.7676 - accuracy: 0.7353 672/3595 [====>.........................] - ETA: 1s - loss: 0.7587 - accuracy: 0.7351 800/3595 [=====>........................] - ETA: 1s - loss: 0.7826 - accuracy: 0.7250 928/3595 [======>.......................] - ETA: 1s - loss: 0.7710 - accuracy: 0.7306 1056/3595 [=======>......................] - ETA: 1s - loss: 0.7656 - accuracy: 0.7330 1184/3595 [========>.....................] - ETA: 1s - loss: 0.7681 - accuracy: 0.7306 1280/3595 [=========>....................] - ETA: 1s - loss: 0.7726 - accuracy: 0.7297 1408/3595 [==========>...................] - ETA: 1s - loss: 0.7747 - accuracy: 0.7322 1536/3595 [===========>..................] - ETA: 1s - loss: 0.7806 - accuracy: 0.7324 1664/3595 [============>.................] - ETA: 0s - loss: 0.7900 - accuracy: 0.7302 1792/3595 [=============>................] - ETA: 0s - loss: 0.7953 - accuracy: 0.7260 1920/3595 [===============>..............] - ETA: 0s - loss: 0.8006 - accuracy: 0.7234 2048/3595 [================>.............] - ETA: 0s - loss: 0.7956 - accuracy: 0.7280 2176/3595 [=================>............] - ETA: 0s - loss: 0.7936 - accuracy: 0.7298 2304/3595 [==================>...........] - ETA: 0s - loss: 0.8010 - accuracy: 0.7270 2432/3595 [===================>..........] - ETA: 0s - loss: 0.8024 - accuracy: 0.7253 2528/3595 [====================>.........] - ETA: 0s - loss: 0.8032 - accuracy: 0.7255 2624/3595 [====================>.........] - ETA: 0s - loss: 0.8026 - accuracy: 0.7264 2752/3595 [=====================>........] - ETA: 0s - loss: 0.8017 - accuracy: 0.7257 2880/3595 [=======================>......] - ETA: 0s - loss: 0.8051 - accuracy: 0.7215 2976/3595 [=======================>......] - ETA: 0s - loss: 0.8038 - accuracy: 0.7214 3104/3595 [========================>.....] - ETA: 0s - loss: 0.8025 - accuracy: 0.7226 3232/3595 [=========================>....] - ETA: 0s - loss: 0.8013 - accuracy: 0.7237 3360/3595 [===========================>..] - ETA: 0s - loss: 0.8034 - accuracy: 0.7232 3488/3595 [============================>.] - ETA: 0s - loss: 0.8049 - accuracy: 0.7228 3595/3595 [==============================] - 2s 561us/sample - loss: 0.8044 - accuracy: 0.7218 - val_loss: 1.0216 - val_accuracy: 0.6440 Epoch 21/28 32/3595 [..............................] - ETA: 1s - loss: 0.9437 - accuracy: 0.7500 160/3595 [>.............................] - ETA: 1s - loss: 0.8399 - accuracy: 0.6938 288/3595 [=>............................] - ETA: 1s - loss: 0.8604 - accuracy: 0.7188 384/3595 [==>...........................] - ETA: 1s - loss: 0.8550 - accuracy: 0.7135 512/3595 [===>..........................] - ETA: 1s - loss: 0.7992 - accuracy: 0.7324 640/3595 [====>.........................] - ETA: 1s - loss: 0.7775 - accuracy: 0.7391 736/3595 [=====>........................] - ETA: 1s - loss: 0.7786 - accuracy: 0.7364 864/3595 [======>.......................] - ETA: 1s - loss: 0.7992 - accuracy: 0.7315 992/3595 [=======>......................] - ETA: 1s - loss: 0.8067 - accuracy: 0.7248 1120/3595 [========>.....................] - ETA: 1s - loss: 0.8031 - accuracy: 0.7259 1248/3595 [=========>....................] - ETA: 1s - loss: 0.7936 - accuracy: 0.7340 1376/3595 [==========>...................] - ETA: 1s - loss: 0.7938 - accuracy: 0.7311 1472/3595 [===========>..................] - ETA: 1s - loss: 0.7923 - accuracy: 0.7262 1600/3595 [============>.................] - ETA: 1s - loss: 0.7857 - accuracy: 0.7294 1728/3595 [=============>................] - ETA: 0s - loss: 0.7873 - accuracy: 0.7297 1856/3595 [==============>...............] - ETA: 0s - loss: 0.7942 - accuracy: 0.7258 1984/3595 [===============>..............] - ETA: 0s - loss: 0.7912 - accuracy: 0.7273 2080/3595 [================>.............] - ETA: 0s - loss: 0.7915 - accuracy: 0.7264 2208/3595 [=================>............] - ETA: 0s - loss: 0.7963 - accuracy: 0.7260 2336/3595 [==================>...........] - ETA: 0s - loss: 0.7930 - accuracy: 0.7256 2464/3595 [===================>..........] - ETA: 0s - loss: 0.7888 - accuracy: 0.7301 2592/3595 [====================>.........] - ETA: 0s - loss: 0.7984 - accuracy: 0.7288 2720/3595 [=====================>........] - ETA: 0s - loss: 0.7966 - accuracy: 0.7294 2816/3595 [======================>.......] - ETA: 0s - loss: 0.7947 - accuracy: 0.7305 2976/3595 [=======================>......] - ETA: 0s - loss: 0.7904 - accuracy: 0.7308 3104/3595 [========================>.....] - ETA: 0s - loss: 0.7921 - accuracy: 0.7297 3232/3595 [=========================>....] - ETA: 0s - loss: 0.7924 - accuracy: 0.7317 3360/3595 [===========================>..] - ETA: 0s - loss: 0.7931 - accuracy: 0.7301 3488/3595 [============================>.] - ETA: 0s - loss: 0.7980 - accuracy: 0.7285 3595/3595 [==============================] - 2s 544us/sample - loss: 0.8041 - accuracy: 0.7266 - val_loss: 1.0140 - val_accuracy: 0.6552 Epoch 22/28 32/3595 [..............................] - ETA: 1s - loss: 0.8140 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 1s - loss: 0.7189 - accuracy: 0.7437 256/3595 [=>............................] - ETA: 1s - loss: 0.7553 - accuracy: 0.7031 384/3595 [==>...........................] - ETA: 1s - loss: 0.7707 - accuracy: 0.7188 512/3595 [===>..........................] - ETA: 1s - loss: 0.7480 - accuracy: 0.7324 640/3595 [====>.........................] - ETA: 1s - loss: 0.7541 - accuracy: 0.7234 768/3595 [=====>........................] - ETA: 1s - loss: 0.7506 - accuracy: 0.7292 864/3595 [======>.......................] - ETA: 1s - loss: 0.7523 - accuracy: 0.7280 992/3595 [=======>......................] - ETA: 1s - loss: 0.7531 - accuracy: 0.7319 1120/3595 [========>.....................] - ETA: 1s - loss: 0.7404 - accuracy: 0.7393 1248/3595 [=========>....................] - ETA: 1s - loss: 0.7424 - accuracy: 0.7364 1376/3595 [==========>...................] - ETA: 1s - loss: 0.7578 - accuracy: 0.7311 1504/3595 [===========>..................] - ETA: 1s - loss: 0.7622 - accuracy: 0.7301 1632/3595 [============>.................] - ETA: 1s - loss: 0.7650 - accuracy: 0.7298 1760/3595 [=============>................] - ETA: 0s - loss: 0.7646 - accuracy: 0.7290 1888/3595 [==============>...............] - ETA: 0s - loss: 0.7592 - accuracy: 0.7341 2016/3595 [===============>..............] - ETA: 0s - loss: 0.7628 - accuracy: 0.7351 2144/3595 [================>.............] - ETA: 0s - loss: 0.7730 - accuracy: 0.7290 2272/3595 [=================>............] - ETA: 0s - loss: 0.7754 - accuracy: 0.7276 2400/3595 [===================>..........] - ETA: 0s - loss: 0.7745 - accuracy: 0.7275 2496/3595 [===================>..........] - ETA: 0s - loss: 0.7799 - accuracy: 0.7268 2624/3595 [====================>.........] - ETA: 0s - loss: 0.7826 - accuracy: 0.7268 2752/3595 [=====================>........] - ETA: 0s - loss: 0.7844 - accuracy: 0.7260 2880/3595 [=======================>......] - ETA: 0s - loss: 0.7828 - accuracy: 0.7271 3008/3595 [========================>.....] - ETA: 0s - loss: 0.7832 - accuracy: 0.7274 3136/3595 [=========================>....] - ETA: 0s - loss: 0.7839 - accuracy: 0.7267 3264/3595 [==========================>...] - ETA: 0s - loss: 0.7810 - accuracy: 0.7292 3392/3595 [===========================>..] - ETA: 0s - loss: 0.7756 - accuracy: 0.7302 3488/3595 [============================>.] - ETA: 0s - loss: 0.7745 - accuracy: 0.7314 3595/3595 [==============================] - 2s 540us/sample - loss: 0.7728 - accuracy: 0.7316 - val_loss: 1.0093 - val_accuracy: 0.6507 Epoch 23/28 32/3595 [..............................] - ETA: 3s - loss: 0.4824 - accuracy: 0.8750 160/3595 [>.............................] - ETA: 2s - loss: 0.7078 - accuracy: 0.7563 288/3595 [=>............................] - ETA: 1s - loss: 0.6698 - accuracy: 0.7778 416/3595 [==>...........................] - ETA: 1s - loss: 0.6471 - accuracy: 0.7909 512/3595 [===>..........................] - ETA: 1s - loss: 0.6232 - accuracy: 0.8008 640/3595 [====>.........................] - ETA: 1s - loss: 0.6502 - accuracy: 0.7812 768/3595 [=====>........................] - ETA: 1s - loss: 0.6415 - accuracy: 0.7865 896/3595 [======>.......................] - ETA: 1s - loss: 0.6559 - accuracy: 0.7824 1024/3595 [=======>......................] - ETA: 1s - loss: 0.6530 - accuracy: 0.7822 1120/3595 [========>.....................] - ETA: 1s - loss: 0.6664 - accuracy: 0.7741 1248/3595 [=========>....................] - ETA: 1s - loss: 0.6693 - accuracy: 0.7740 1376/3595 [==========>...................] - ETA: 1s - loss: 0.6938 - accuracy: 0.7674 1472/3595 [===========>..................] - ETA: 1s - loss: 0.6992 - accuracy: 0.7636 1568/3595 [============>.................] - ETA: 1s - loss: 0.7065 - accuracy: 0.7615 1664/3595 [============>.................] - ETA: 1s - loss: 0.7050 - accuracy: 0.7626 1760/3595 [=============>................] - ETA: 1s - loss: 0.7042 - accuracy: 0.7625 1856/3595 [==============>...............] - ETA: 0s - loss: 0.7004 - accuracy: 0.7624 1984/3595 [===============>..............] - ETA: 0s - loss: 0.6974 - accuracy: 0.7646 2112/3595 [================>.............] - ETA: 0s - loss: 0.6988 - accuracy: 0.7623 2208/3595 [=================>............] - ETA: 0s - loss: 0.6960 - accuracy: 0.7631 2336/3595 [==================>...........] - ETA: 0s - loss: 0.7035 - accuracy: 0.7620 2464/3595 [===================>..........] - ETA: 0s - loss: 0.7122 - accuracy: 0.7577 2592/3595 [====================>.........] - ETA: 0s - loss: 0.7142 - accuracy: 0.7573 2720/3595 [=====================>........] - ETA: 0s - loss: 0.7093 - accuracy: 0.7588 2848/3595 [======================>.......] - ETA: 0s - loss: 0.7193 - accuracy: 0.7532 2976/3595 [=======================>......] - ETA: 0s - loss: 0.7237 - accuracy: 0.7493 3104/3595 [========================>.....] - ETA: 0s - loss: 0.7211 - accuracy: 0.7500 3232/3595 [=========================>....] - ETA: 0s - loss: 0.7224 - accuracy: 0.7503 3360/3595 [===========================>..] - ETA: 0s - loss: 0.7212 - accuracy: 0.7512 3456/3595 [===========================>..] - ETA: 0s - loss: 0.7273 - accuracy: 0.7500 3584/3595 [============================>.] - ETA: 0s - loss: 0.7280 - accuracy: 0.7506 3595/3595 [==============================] - 2s 561us/sample - loss: 0.7288 - accuracy: 0.7502 - val_loss: 0.9858 - val_accuracy: 0.6607 Epoch 24/28 32/3595 [..............................] - ETA: 1s - loss: 0.7514 - accuracy: 0.7500 128/3595 [>.............................] - ETA: 2s - loss: 0.7968 - accuracy: 0.7656 256/3595 [=>............................] - ETA: 1s - loss: 0.7801 - accuracy: 0.7383 384/3595 [==>...........................] - ETA: 1s - loss: 0.7635 - accuracy: 0.7500 512/3595 [===>..........................] - ETA: 1s - loss: 0.7330 - accuracy: 0.7617 640/3595 [====>.........................] - ETA: 1s - loss: 0.7500 - accuracy: 0.7500 768/3595 [=====>........................] - ETA: 1s - loss: 0.7471 - accuracy: 0.7526 896/3595 [======>.......................] - ETA: 1s - loss: 0.7418 - accuracy: 0.7545 1024/3595 [=======>......................] - ETA: 1s - loss: 0.7361 - accuracy: 0.7549 1152/3595 [========>.....................] - ETA: 1s - loss: 0.7328 - accuracy: 0.7517 1280/3595 [=========>....................] - ETA: 1s - loss: 0.7204 - accuracy: 0.7523 1408/3595 [==========>...................] - ETA: 1s - loss: 0.7264 - accuracy: 0.7500 1536/3595 [===========>..................] - ETA: 1s - loss: 0.7236 - accuracy: 0.7493 1664/3595 [============>.................] - ETA: 0s - loss: 0.7166 - accuracy: 0.7542 1760/3595 [=============>................] - ETA: 0s - loss: 0.7121 - accuracy: 0.7585 1888/3595 [==============>...............] - ETA: 0s - loss: 0.7124 - accuracy: 0.7595 2016/3595 [===============>..............] - ETA: 0s - loss: 0.7127 - accuracy: 0.7584 2144/3595 [================>.............] - ETA: 0s - loss: 0.7087 - accuracy: 0.7607 2272/3595 [=================>............] - ETA: 0s - loss: 0.7041 - accuracy: 0.7610 2400/3595 [===================>..........] - ETA: 0s - loss: 0.7121 - accuracy: 0.7571 2528/3595 [====================>.........] - ETA: 0s - loss: 0.7081 - accuracy: 0.7587 2656/3595 [=====================>........] - ETA: 0s - loss: 0.7122 - accuracy: 0.7556 2784/3595 [======================>.......] - ETA: 0s - loss: 0.7048 - accuracy: 0.7572 2912/3595 [=======================>......] - ETA: 0s - loss: 0.7086 - accuracy: 0.7555 3008/3595 [========================>.....] - ETA: 0s - loss: 0.7090 - accuracy: 0.7557 3136/3595 [=========================>....] - ETA: 0s - loss: 0.7097 - accuracy: 0.7561 3264/3595 [==========================>...] - ETA: 0s - loss: 0.7094 - accuracy: 0.7555 3392/3595 [===========================>..] - ETA: 0s - loss: 0.7129 - accuracy: 0.7527 3520/3595 [============================>.] - ETA: 0s - loss: 0.7090 - accuracy: 0.7548 3595/3595 [==============================] - 2s 548us/sample - loss: 0.7089 - accuracy: 0.7547 - val_loss: 0.9930 - val_accuracy: 0.6474 Epoch 25/28 32/3595 [..............................] - ETA: 3s - loss: 0.5510 - accuracy: 0.7812 160/3595 [>.............................] - ETA: 2s - loss: 0.6983 - accuracy: 0.7063 288/3595 [=>............................] - ETA: 1s - loss: 0.7267 - accuracy: 0.7153 416/3595 [==>...........................] - ETA: 1s - loss: 0.7044 - accuracy: 0.7236 512/3595 [===>..........................] - ETA: 1s - loss: 0.6603 - accuracy: 0.7559 640/3595 [====>.........................] - ETA: 1s - loss: 0.6769 - accuracy: 0.7500 768/3595 [=====>........................] - ETA: 1s - loss: 0.6874 - accuracy: 0.7448 896/3595 [======>.......................] - ETA: 1s - loss: 0.6766 - accuracy: 0.7522 992/3595 [=======>......................] - ETA: 1s - loss: 0.6829 - accuracy: 0.7520 1120/3595 [========>.....................] - ETA: 1s - loss: 0.6828 - accuracy: 0.7527 1248/3595 [=========>....................] - ETA: 1s - loss: 0.6804 - accuracy: 0.7564 1376/3595 [==========>...................] - ETA: 1s - loss: 0.6801 - accuracy: 0.7594 1504/3595 [===========>..................] - ETA: 1s - loss: 0.6771 - accuracy: 0.7606 1632/3595 [============>.................] - ETA: 1s - loss: 0.6883 - accuracy: 0.7561 1728/3595 [=============>................] - ETA: 0s - loss: 0.6828 - accuracy: 0.7598 1856/3595 [==============>...............] - ETA: 0s - loss: 0.6817 - accuracy: 0.7619 1984/3595 [===============>..............] - ETA: 0s - loss: 0.6926 - accuracy: 0.7601 2112/3595 [================>.............] - ETA: 0s - loss: 0.6858 - accuracy: 0.7642 2208/3595 [=================>............] - ETA: 0s - loss: 0.6878 - accuracy: 0.7622 2336/3595 [==================>...........] - ETA: 0s - loss: 0.6889 - accuracy: 0.7616 2464/3595 [===================>..........] - ETA: 0s - loss: 0.6909 - accuracy: 0.7626 2592/3595 [====================>.........] - ETA: 0s - loss: 0.6898 - accuracy: 0.7639 2720/3595 [=====================>........] - ETA: 0s - loss: 0.6889 - accuracy: 0.7647 2848/3595 [======================>.......] - ETA: 0s - loss: 0.6920 - accuracy: 0.7633 2976/3595 [=======================>......] - ETA: 0s - loss: 0.6920 - accuracy: 0.7614 3104/3595 [========================>.....] - ETA: 0s - loss: 0.6956 - accuracy: 0.7610 3232/3595 [=========================>....] - ETA: 0s - loss: 0.6939 - accuracy: 0.7602 3328/3595 [==========================>...] - ETA: 0s - loss: 0.6959 - accuracy: 0.7596 3456/3595 [===========================>..] - ETA: 0s - loss: 0.6971 - accuracy: 0.7587 3584/3595 [============================>.] - ETA: 0s - loss: 0.6995 - accuracy: 0.7561 3595/3595 [==============================] - 2s 553us/sample - loss: 0.6981 - accuracy: 0.7569 - val_loss: 0.9667 - val_accuracy: 0.6719 Epoch 26/28 32/3595 [..............................] - ETA: 1s - loss: 0.8947 - accuracy: 0.6250 160/3595 [>.............................] - ETA: 2s - loss: 0.6352 - accuracy: 0.7500 288/3595 [=>............................] - ETA: 1s - loss: 0.6177 - accuracy: 0.7812 416/3595 [==>...........................] - ETA: 1s - loss: 0.5820 - accuracy: 0.7933 512/3595 [===>..........................] - ETA: 1s - loss: 0.5746 - accuracy: 0.7969 608/3595 [====>.........................] - ETA: 1s - loss: 0.5787 - accuracy: 0.7928 704/3595 [====>.........................] - ETA: 1s - loss: 0.5837 - accuracy: 0.8011 832/3595 [=====>........................] - ETA: 1s - loss: 0.5832 - accuracy: 0.7981 928/3595 [======>.......................] - ETA: 1s - loss: 0.6006 - accuracy: 0.7953 1056/3595 [=======>......................] - ETA: 1s - loss: 0.6136 - accuracy: 0.7869 1184/3595 [========>.....................] - ETA: 1s - loss: 0.6183 - accuracy: 0.7880 1312/3595 [=========>....................] - ETA: 1s - loss: 0.6184 - accuracy: 0.7889 1440/3595 [===========>..................] - ETA: 1s - loss: 0.6266 - accuracy: 0.7875 1568/3595 [============>.................] - ETA: 1s - loss: 0.6244 - accuracy: 0.7895 1696/3595 [=============>................] - ETA: 1s - loss: 0.6230 - accuracy: 0.7919 1824/3595 [==============>...............] - ETA: 0s - loss: 0.6222 - accuracy: 0.7911 1952/3595 [===============>..............] - ETA: 0s - loss: 0.6231 - accuracy: 0.7879 2080/3595 [================>.............] - ETA: 0s - loss: 0.6328 - accuracy: 0.7837 2208/3595 [=================>............] - ETA: 0s - loss: 0.6375 - accuracy: 0.7831 2336/3595 [==================>...........] - ETA: 0s - loss: 0.6448 - accuracy: 0.7808 2432/3595 [===================>..........] - ETA: 0s - loss: 0.6491 - accuracy: 0.7796 2560/3595 [====================>.........] - ETA: 0s - loss: 0.6492 - accuracy: 0.7789 2688/3595 [=====================>........] - ETA: 0s - loss: 0.6499 - accuracy: 0.7798 2816/3595 [======================>.......] - ETA: 0s - loss: 0.6488 - accuracy: 0.7791 2944/3595 [=======================>......] - ETA: 0s - loss: 0.6525 - accuracy: 0.7768 3072/3595 [========================>.....] - ETA: 0s - loss: 0.6555 - accuracy: 0.7754 3200/3595 [=========================>....] - ETA: 0s - loss: 0.6562 - accuracy: 0.7756 3328/3595 [==========================>...] - ETA: 0s - loss: 0.6535 - accuracy: 0.7764 3456/3595 [===========================>..] - ETA: 0s - loss: 0.6584 - accuracy: 0.7760 3584/3595 [============================>.] - ETA: 0s - loss: 0.6612 - accuracy: 0.7757 3595/3595 [==============================] - 2s 548us/sample - loss: 0.6611 - accuracy: 0.7758 - val_loss: 0.9832 - val_accuracy: 0.6574 Epoch 27/28 32/3595 [..............................] - ETA: 1s - loss: 0.4223 - accuracy: 0.9062 128/3595 [>.............................] - ETA: 2s - loss: 0.6480 - accuracy: 0.7500 256/3595 [=>............................] - ETA: 1s - loss: 0.5581 - accuracy: 0.7969 384/3595 [==>...........................] - ETA: 1s - loss: 0.6082 - accuracy: 0.7891 512/3595 [===>..........................] - ETA: 1s - loss: 0.6251 - accuracy: 0.7891 608/3595 [====>.........................] - ETA: 1s - loss: 0.6391 - accuracy: 0.7780 736/3595 [=====>........................] - ETA: 1s - loss: 0.6369 - accuracy: 0.7840 864/3595 [======>.......................] - ETA: 1s - loss: 0.6317 - accuracy: 0.7836 960/3595 [=======>......................] - ETA: 1s - loss: 0.6253 - accuracy: 0.7906 1088/3595 [========>.....................] - ETA: 1s - loss: 0.6409 - accuracy: 0.7849 1184/3595 [========>.....................] - ETA: 1s - loss: 0.6540 - accuracy: 0.7829 1312/3595 [=========>....................] - ETA: 1s - loss: 0.6453 - accuracy: 0.7889 1440/3595 [===========>..................] - ETA: 1s - loss: 0.6589 - accuracy: 0.7840 1536/3595 [===========>..................] - ETA: 1s - loss: 0.6517 - accuracy: 0.7852 1664/3595 [============>.................] - ETA: 1s - loss: 0.6616 - accuracy: 0.7806 1792/3595 [=============>................] - ETA: 0s - loss: 0.6601 - accuracy: 0.7807 1920/3595 [===============>..............] - ETA: 0s - loss: 0.6603 - accuracy: 0.7802 2048/3595 [================>.............] - ETA: 0s - loss: 0.6588 - accuracy: 0.7822 2176/3595 [=================>............] - ETA: 0s - loss: 0.6592 - accuracy: 0.7835 2304/3595 [==================>...........] - ETA: 0s - loss: 0.6573 - accuracy: 0.7826 2400/3595 [===================>..........] - ETA: 0s - loss: 0.6588 - accuracy: 0.7800 2528/3595 [====================>.........] - ETA: 0s - loss: 0.6684 - accuracy: 0.7749 2656/3595 [=====================>........] - ETA: 0s - loss: 0.6654 - accuracy: 0.7767 2784/3595 [======================>.......] - ETA: 0s - loss: 0.6669 - accuracy: 0.7755 2880/3595 [=======================>......] - ETA: 0s - loss: 0.6729 - accuracy: 0.7736 3008/3595 [========================>.....] - ETA: 0s - loss: 0.6740 - accuracy: 0.7726 3136/3595 [=========================>....] - ETA: 0s - loss: 0.6685 - accuracy: 0.7736 3264/3595 [==========================>...] - ETA: 0s - loss: 0.6688 - accuracy: 0.7739 3392/3595 [===========================>..] - ETA: 0s - loss: 0.6694 - accuracy: 0.7739 3488/3595 [============================>.] - ETA: 0s - loss: 0.6646 - accuracy: 0.7755 3595/3595 [==============================] - 2s 557us/sample - loss: 0.6631 - accuracy: 0.7764 - val_loss: 0.9960 - val_accuracy: 0.6563 Epoch 28/28 32/3595 [..............................] - ETA: 1s - loss: 0.5972 - accuracy: 0.7812 160/3595 [>.............................] - ETA: 1s - loss: 0.5074 - accuracy: 0.8562 288/3595 [=>............................] - ETA: 1s - loss: 0.5398 - accuracy: 0.8368 416/3595 [==>...........................] - ETA: 1s - loss: 0.5506 - accuracy: 0.8341 512/3595 [===>..........................] - ETA: 1s - loss: 0.5676 - accuracy: 0.8145 640/3595 [====>.........................] - ETA: 1s - loss: 0.5744 - accuracy: 0.8188 768/3595 [=====>........................] - ETA: 1s - loss: 0.5884 - accuracy: 0.8112 896/3595 [======>.......................] - ETA: 1s - loss: 0.6038 - accuracy: 0.8036 992/3595 [=======>......................] - ETA: 1s - loss: 0.5953 - accuracy: 0.8075 1120/3595 [========>.....................] - ETA: 1s - loss: 0.5911 - accuracy: 0.8045 1248/3595 [=========>....................] - ETA: 1s - loss: 0.5836 - accuracy: 0.8053 1376/3595 [==========>...................] - ETA: 1s - loss: 0.5967 - accuracy: 0.7980 1472/3595 [===========>..................] - ETA: 1s - loss: 0.6049 - accuracy: 0.7921 1600/3595 [============>.................] - ETA: 1s - loss: 0.6136 - accuracy: 0.7919 1728/3595 [=============>................] - ETA: 0s - loss: 0.6215 - accuracy: 0.7882 1856/3595 [==============>...............] - ETA: 0s - loss: 0.6308 - accuracy: 0.7856 1984/3595 [===============>..............] - ETA: 0s - loss: 0.6332 - accuracy: 0.7833 2112/3595 [================>.............] - ETA: 0s - loss: 0.6302 - accuracy: 0.7855 2240/3595 [=================>............] - ETA: 0s - loss: 0.6275 - accuracy: 0.7853 2336/3595 [==================>...........] - ETA: 0s - loss: 0.6252 - accuracy: 0.7851 2464/3595 [===================>..........] - ETA: 0s - loss: 0.6273 - accuracy: 0.7857 2592/3595 [====================>.........] - ETA: 0s - loss: 0.6349 - accuracy: 0.7820 2720/3595 [=====================>........] - ETA: 0s - loss: 0.6354 - accuracy: 0.7831 2848/3595 [======================>.......] - ETA: 0s - loss: 0.6328 - accuracy: 0.7841 2944/3595 [=======================>......] - ETA: 0s - loss: 0.6353 - accuracy: 0.7823 3040/3595 [========================>.....] - ETA: 0s - loss: 0.6401 - accuracy: 0.7799 3168/3595 [=========================>....] - ETA: 0s - loss: 0.6427 - accuracy: 0.7781 3264/3595 [==========================>...] - ETA: 0s - loss: 0.6412 - accuracy: 0.7800 3360/3595 [===========================>..] - ETA: 0s - loss: 0.6378 - accuracy: 0.7801 3488/3595 [============================>.] - ETA: 0s - loss: 0.6412 - accuracy: 0.7795 3584/3595 [============================>.] - ETA: 0s - loss: 0.6427 - accuracy: 0.7779 3595/3595 [==============================] - 2s 561us/sample - loss: 0.6430 - accuracy: 0.7777 - val_loss: 0.9679 - val_accuracy: 0.6630 Evaluating model for iteration 2... 1498/1498 - 0s - loss: 0.9598 - accuracy: 0.6475 Accuracy for iteration 2 0.6475300192832947 Training model for iteration 3... Train on 3595 samples, validate on 899 samples Epoch 1/28 32/3595 [..............................] - ETA: 50s - loss: 3.3041 - accuracy: 0.0938 160/3595 [>.............................] - ETA: 11s - loss: 3.1716 - accuracy: 0.0688 288/3595 [=>............................] - ETA: 6s - loss: 3.0885 - accuracy: 0.1007 416/3595 [==>...........................] - ETA: 5s - loss: 2.9996 - accuracy: 0.1058 544/3595 [===>..........................] - ETA: 4s - loss: 2.9685 - accuracy: 0.1066 640/3595 [====>.........................] - ETA: 3s - loss: 2.9461 - accuracy: 0.1141 768/3595 [=====>........................] - ETA: 3s - loss: 2.9129 - accuracy: 0.1237 896/3595 [======>.......................] - ETA: 2s - loss: 2.8928 - accuracy: 0.1272 992/3595 [=======>......................] - ETA: 2s - loss: 2.8741 - accuracy: 0.1310 1120/3595 [========>.....................] - ETA: 2s - loss: 2.8496 - accuracy: 0.1330 1248/3595 [=========>....................] - ETA: 2s - loss: 2.8290 - accuracy: 0.1386 1376/3595 [==========>...................] - ETA: 1s - loss: 2.8027 - accuracy: 0.1475 1504/3595 [===========>..................] - ETA: 1s - loss: 2.7842 - accuracy: 0.1516 1632/3595 [============>.................] - ETA: 1s - loss: 2.7473 - accuracy: 0.1605 1760/3595 [=============>................] - ETA: 1s - loss: 2.7151 - accuracy: 0.1688 1888/3595 [==============>...............] - ETA: 1s - loss: 2.6932 - accuracy: 0.1743 2016/3595 [===============>..............] - ETA: 1s - loss: 2.6773 - accuracy: 0.1761 2144/3595 [================>.............] - ETA: 1s - loss: 2.6504 - accuracy: 0.1824 2272/3595 [=================>............] - ETA: 0s - loss: 2.6349 - accuracy: 0.1827 2400/3595 [===================>..........] - ETA: 0s - loss: 2.6136 - accuracy: 0.1896 2496/3595 [===================>..........] - ETA: 0s - loss: 2.6011 - accuracy: 0.1907 2624/3595 [====================>.........] - ETA: 0s - loss: 2.5764 - accuracy: 0.1959 2752/3595 [=====================>........] - ETA: 0s - loss: 2.5558 - accuracy: 0.2009 2880/3595 [=======================>......] - ETA: 0s - loss: 2.5514 - accuracy: 0.2017 2976/3595 [=======================>......] - ETA: 0s - loss: 2.5410 - accuracy: 0.2046 3104/3595 [========================>.....] - ETA: 0s - loss: 2.5235 - accuracy: 0.2097 3232/3595 [=========================>....] - ETA: 0s - loss: 2.5161 - accuracy: 0.2107 3360/3595 [===========================>..] - ETA: 0s - loss: 2.5095 - accuracy: 0.2131 3456/3595 [===========================>..] - ETA: 0s - loss: 2.4993 - accuracy: 0.2147 3584/3595 [============================>.] - ETA: 0s - loss: 2.4892 - accuracy: 0.2157 3595/3595 [==============================] - 3s 787us/sample - loss: 2.4872 - accuracy: 0.2161 - val_loss: 2.0509 - val_accuracy: 0.2781 Epoch 2/28 32/3595 [..............................] - ETA: 3s - loss: 2.0725 - accuracy: 0.4062 160/3595 [>.............................] - ETA: 2s - loss: 1.9972 - accuracy: 0.3625 288/3595 [=>............................] - ETA: 1s - loss: 2.0506 - accuracy: 0.3403 416/3595 [==>...........................] - ETA: 1s - loss: 2.0664 - accuracy: 0.3317 544/3595 [===>..........................] - ETA: 1s - loss: 2.0550 - accuracy: 0.3254 672/3595 [====>.........................] - ETA: 1s - loss: 2.0606 - accuracy: 0.3244 800/3595 [=====>........................] - ETA: 1s - loss: 2.0427 - accuracy: 0.3288 896/3595 [======>.......................] - ETA: 1s - loss: 2.0270 - accuracy: 0.3337 1024/3595 [=======>......................] - ETA: 1s - loss: 2.0293 - accuracy: 0.3291 1152/3595 [========>.....................] - ETA: 1s - loss: 2.0286 - accuracy: 0.3238 1280/3595 [=========>....................] - ETA: 1s - loss: 2.0142 - accuracy: 0.3250 1408/3595 [==========>...................] - ETA: 1s - loss: 2.0001 - accuracy: 0.3288 1504/3595 [===========>..................] - ETA: 1s - loss: 1.9987 - accuracy: 0.3291 1600/3595 [============>.................] - ETA: 1s - loss: 2.0042 - accuracy: 0.3237 1696/3595 [=============>................] - ETA: 1s - loss: 2.0118 - accuracy: 0.3237 1792/3595 [=============>................] - ETA: 0s - loss: 2.0043 - accuracy: 0.3242 1888/3595 [==============>...............] - ETA: 0s - loss: 2.0136 - accuracy: 0.3210 2016/3595 [===============>..............] - ETA: 0s - loss: 2.0051 - accuracy: 0.3274 2112/3595 [================>.............] - ETA: 0s - loss: 1.9883 - accuracy: 0.3314 2240/3595 [=================>............] - ETA: 0s - loss: 1.9813 - accuracy: 0.3321 2368/3595 [==================>...........] - ETA: 0s - loss: 1.9838 - accuracy: 0.3319 2496/3595 [===================>..........] - ETA: 0s - loss: 1.9874 - accuracy: 0.3325 2624/3595 [====================>.........] - ETA: 0s - loss: 1.9911 - accuracy: 0.3319 2752/3595 [=====================>........] - ETA: 0s - loss: 1.9857 - accuracy: 0.3325 2880/3595 [=======================>......] - ETA: 0s - loss: 1.9763 - accuracy: 0.3337 3008/3595 [========================>.....] - ETA: 0s - loss: 1.9722 - accuracy: 0.3344 3136/3595 [=========================>....] - ETA: 0s - loss: 1.9692 - accuracy: 0.3358 3264/3595 [==========================>...] - ETA: 0s - loss: 1.9586 - accuracy: 0.3373 3392/3595 [===========================>..] - ETA: 0s - loss: 1.9490 - accuracy: 0.3379 3520/3595 [============================>.] - ETA: 0s - loss: 1.9443 - accuracy: 0.3395 3595/3595 [==============================] - 2s 565us/sample - loss: 1.9446 - accuracy: 0.3388 - val_loss: 1.7059 - val_accuracy: 0.3993 Epoch 3/28 32/3595 [..............................] - ETA: 1s - loss: 1.3480 - accuracy: 0.5000 160/3595 [>.............................] - ETA: 1s - loss: 1.9050 - accuracy: 0.3562 256/3595 [=>............................] - ETA: 1s - loss: 1.8051 - accuracy: 0.3828 384/3595 [==>...........................] - ETA: 1s - loss: 1.8136 - accuracy: 0.3802 512/3595 [===>..........................] - ETA: 1s - loss: 1.7634 - accuracy: 0.3926 608/3595 [====>.........................] - ETA: 1s - loss: 1.7648 - accuracy: 0.3849 736/3595 [=====>........................] - ETA: 1s - loss: 1.7613 - accuracy: 0.3832 864/3595 [======>.......................] - ETA: 1s - loss: 1.7408 - accuracy: 0.3935 960/3595 [=======>......................] - ETA: 1s - loss: 1.7486 - accuracy: 0.3948 1088/3595 [========>.....................] - ETA: 1s - loss: 1.7270 - accuracy: 0.4044 1216/3595 [=========>....................] - ETA: 1s - loss: 1.7262 - accuracy: 0.4030 1312/3595 [=========>....................] - ETA: 1s - loss: 1.7373 - accuracy: 0.3979 1440/3595 [===========>..................] - ETA: 1s - loss: 1.7510 - accuracy: 0.3931 1568/3595 [============>.................] - ETA: 1s - loss: 1.7484 - accuracy: 0.3941 1696/3595 [=============>................] - ETA: 0s - loss: 1.7435 - accuracy: 0.3950 1824/3595 [==============>...............] - ETA: 0s - loss: 1.7325 - accuracy: 0.3997 1952/3595 [===============>..............] - ETA: 0s - loss: 1.7325 - accuracy: 0.4022 2080/3595 [================>.............] - ETA: 0s - loss: 1.7344 - accuracy: 0.4005 2208/3595 [=================>............] - ETA: 0s - loss: 1.7384 - accuracy: 0.4022 2336/3595 [==================>...........] - ETA: 0s - loss: 1.7341 - accuracy: 0.4037 2464/3595 [===================>..........] - ETA: 0s - loss: 1.7352 - accuracy: 0.4038 2592/3595 [====================>.........] - ETA: 0s - loss: 1.7399 - accuracy: 0.4008 2688/3595 [=====================>........] - ETA: 0s - loss: 1.7430 - accuracy: 0.4018 2816/3595 [======================>.......] - ETA: 0s - loss: 1.7389 - accuracy: 0.4023 2944/3595 [=======================>......] - ETA: 0s - loss: 1.7354 - accuracy: 0.4042 3072/3595 [========================>.....] - ETA: 0s - loss: 1.7307 - accuracy: 0.4062 3200/3595 [=========================>....] - ETA: 0s - loss: 1.7312 - accuracy: 0.4034 3328/3595 [==========================>...] - ETA: 0s - loss: 1.7377 - accuracy: 0.3990 3424/3595 [===========================>..] - ETA: 0s - loss: 1.7431 - accuracy: 0.3975 3552/3595 [============================>.] - ETA: 0s - loss: 1.7348 - accuracy: 0.4003 3595/3595 [==============================] - 2s 552us/sample - loss: 1.7322 - accuracy: 0.4011 - val_loss: 1.5395 - val_accuracy: 0.4594 Epoch 4/28 32/3595 [..............................] - ETA: 1s - loss: 1.6702 - accuracy: 0.5000 160/3595 [>.............................] - ETA: 1s - loss: 1.6994 - accuracy: 0.4187 256/3595 [=>............................] - ETA: 1s - loss: 1.6795 - accuracy: 0.4297 384/3595 [==>...........................] - ETA: 1s - loss: 1.6109 - accuracy: 0.4557 512/3595 [===>..........................] - ETA: 1s - loss: 1.6317 - accuracy: 0.4531 640/3595 [====>.........................] - ETA: 1s - loss: 1.6231 - accuracy: 0.4484 768/3595 [=====>........................] - ETA: 1s - loss: 1.6240 - accuracy: 0.4427 896/3595 [======>.......................] - ETA: 1s - loss: 1.6222 - accuracy: 0.4397 1024/3595 [=======>......................] - ETA: 1s - loss: 1.6353 - accuracy: 0.4404 1120/3595 [========>.....................] - ETA: 1s - loss: 1.6333 - accuracy: 0.4357 1248/3595 [=========>....................] - ETA: 1s - loss: 1.6046 - accuracy: 0.4447 1376/3595 [==========>...................] - ETA: 1s - loss: 1.6135 - accuracy: 0.4404 1504/3595 [===========>..................] - ETA: 1s - loss: 1.6006 - accuracy: 0.4461 1632/3595 [============>.................] - ETA: 1s - loss: 1.6004 - accuracy: 0.4473 1760/3595 [=============>................] - ETA: 0s - loss: 1.6022 - accuracy: 0.4455 1888/3595 [==============>...............] - ETA: 0s - loss: 1.5948 - accuracy: 0.4513 2016/3595 [===============>..............] - ETA: 0s - loss: 1.5822 - accuracy: 0.4529 2112/3595 [================>.............] - ETA: 0s - loss: 1.5774 - accuracy: 0.4541 2240/3595 [=================>............] - ETA: 0s - loss: 1.5662 - accuracy: 0.4580 2368/3595 [==================>...........] - ETA: 0s - loss: 1.5558 - accuracy: 0.4599 2496/3595 [===================>..........] - ETA: 0s - loss: 1.5702 - accuracy: 0.4559 2592/3595 [====================>.........] - ETA: 0s - loss: 1.5733 - accuracy: 0.4564 2720/3595 [=====================>........] - ETA: 0s - loss: 1.5716 - accuracy: 0.4581 2848/3595 [======================>.......] - ETA: 0s - loss: 1.5703 - accuracy: 0.4586 2976/3595 [=======================>......] - ETA: 0s - loss: 1.5670 - accuracy: 0.4587 3072/3595 [========================>.....] - ETA: 0s - loss: 1.5579 - accuracy: 0.4613 3200/3595 [=========================>....] - ETA: 0s - loss: 1.5609 - accuracy: 0.4597 3328/3595 [==========================>...] - ETA: 0s - loss: 1.5514 - accuracy: 0.4621 3424/3595 [===========================>..] - ETA: 0s - loss: 1.5487 - accuracy: 0.4620 3552/3595 [============================>.] - ETA: 0s - loss: 1.5566 - accuracy: 0.4581 3595/3595 [==============================] - 2s 556us/sample - loss: 1.5579 - accuracy: 0.4576 - val_loss: 1.4275 - val_accuracy: 0.5083 Epoch 5/28 32/3595 [..............................] - ETA: 1s - loss: 1.6681 - accuracy: 0.4688 128/3595 [>.............................] - ETA: 2s - loss: 1.3444 - accuracy: 0.5156 224/3595 [>.............................] - ETA: 2s - loss: 1.3478 - accuracy: 0.5402 320/3595 [=>............................] - ETA: 2s - loss: 1.4452 - accuracy: 0.4969 448/3595 [==>...........................] - ETA: 1s - loss: 1.4115 - accuracy: 0.5112 544/3595 [===>..........................] - ETA: 1s - loss: 1.3825 - accuracy: 0.5165 672/3595 [====>.........................] - ETA: 1s - loss: 1.4353 - accuracy: 0.5104 800/3595 [=====>........................] - ETA: 1s - loss: 1.4063 - accuracy: 0.5125 928/3595 [======>.......................] - ETA: 1s - loss: 1.4163 - accuracy: 0.5054 1056/3595 [=======>......................] - ETA: 1s - loss: 1.4487 - accuracy: 0.4896 1184/3595 [========>.....................] - ETA: 1s - loss: 1.4604 - accuracy: 0.4856 1280/3595 [=========>....................] - ETA: 1s - loss: 1.4569 - accuracy: 0.4852 1408/3595 [==========>...................] - ETA: 1s - loss: 1.4548 - accuracy: 0.4936 1536/3595 [===========>..................] - ETA: 1s - loss: 1.4548 - accuracy: 0.4902 1664/3595 [============>.................] - ETA: 1s - loss: 1.4665 - accuracy: 0.4886 1792/3595 [=============>................] - ETA: 0s - loss: 1.4712 - accuracy: 0.4833 1920/3595 [===============>..............] - ETA: 0s - loss: 1.4646 - accuracy: 0.4844 2048/3595 [================>.............] - ETA: 0s - loss: 1.4663 - accuracy: 0.4834 2176/3595 [=================>............] - ETA: 0s - loss: 1.4609 - accuracy: 0.4858 2304/3595 [==================>...........] - ETA: 0s - loss: 1.4642 - accuracy: 0.4874 2432/3595 [===================>..........] - ETA: 0s - loss: 1.4570 - accuracy: 0.4926 2560/3595 [====================>.........] - ETA: 0s - loss: 1.4588 - accuracy: 0.4918 2688/3595 [=====================>........] - ETA: 0s - loss: 1.4578 - accuracy: 0.4914 2816/3595 [======================>.......] - ETA: 0s - loss: 1.4550 - accuracy: 0.4925 2944/3595 [=======================>......] - ETA: 0s - loss: 1.4543 - accuracy: 0.4925 3072/3595 [========================>.....] - ETA: 0s - loss: 1.4539 - accuracy: 0.4941 3200/3595 [=========================>....] - ETA: 0s - loss: 1.4599 - accuracy: 0.4928 3328/3595 [==========================>...] - ETA: 0s - loss: 1.4617 - accuracy: 0.4919 3456/3595 [===========================>..] - ETA: 0s - loss: 1.4614 - accuracy: 0.4899 3584/3595 [============================>.] - ETA: 0s - loss: 1.4594 - accuracy: 0.4908 3595/3595 [==============================] - 2s 561us/sample - loss: 1.4605 - accuracy: 0.4907 - val_loss: 1.3665 - val_accuracy: 0.5117 Epoch 6/28 32/3595 [..............................] - ETA: 1s - loss: 0.9105 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 1s - loss: 1.4330 - accuracy: 0.5000 288/3595 [=>............................] - ETA: 1s - loss: 1.4061 - accuracy: 0.5208 416/3595 [==>...........................] - ETA: 1s - loss: 1.3608 - accuracy: 0.5168 544/3595 [===>..........................] - ETA: 1s - loss: 1.3729 - accuracy: 0.5202 672/3595 [====>.........................] - ETA: 1s - loss: 1.3954 - accuracy: 0.5164 768/3595 [=====>........................] - ETA: 1s - loss: 1.4019 - accuracy: 0.5052 896/3595 [======>.......................] - ETA: 1s - loss: 1.4038 - accuracy: 0.5022 1024/3595 [=======>......................] - ETA: 1s - loss: 1.4093 - accuracy: 0.4980 1152/3595 [========>.....................] - ETA: 1s - loss: 1.3918 - accuracy: 0.4983 1248/3595 [=========>....................] - ETA: 1s - loss: 1.3969 - accuracy: 0.4960 1376/3595 [==========>...................] - ETA: 1s - loss: 1.3951 - accuracy: 0.4906 1504/3595 [===========>..................] - ETA: 1s - loss: 1.3937 - accuracy: 0.4934 1632/3595 [============>.................] - ETA: 1s - loss: 1.3952 - accuracy: 0.4939 1760/3595 [=============>................] - ETA: 0s - loss: 1.3928 - accuracy: 0.4977 1888/3595 [==============>...............] - ETA: 0s - loss: 1.3826 - accuracy: 0.5021 2016/3595 [===============>..............] - ETA: 0s - loss: 1.3791 - accuracy: 0.5050 2112/3595 [================>.............] - ETA: 0s - loss: 1.3762 - accuracy: 0.5099 2240/3595 [=================>............] - ETA: 0s - loss: 1.3736 - accuracy: 0.5089 2368/3595 [==================>...........] - ETA: 0s - loss: 1.3754 - accuracy: 0.5059 2496/3595 [===================>..........] - ETA: 0s - loss: 1.3805 - accuracy: 0.5052 2624/3595 [====================>.........] - ETA: 0s - loss: 1.3760 - accuracy: 0.5042 2752/3595 [=====================>........] - ETA: 0s - loss: 1.3735 - accuracy: 0.5040 2880/3595 [=======================>......] - ETA: 0s - loss: 1.3704 - accuracy: 0.5059 3008/3595 [========================>.....] - ETA: 0s - loss: 1.3689 - accuracy: 0.5043 3104/3595 [========================>.....] - ETA: 0s - loss: 1.3705 - accuracy: 0.5055 3232/3595 [=========================>....] - ETA: 0s - loss: 1.3811 - accuracy: 0.5037 3360/3595 [===========================>..] - ETA: 0s - loss: 1.3778 - accuracy: 0.5042 3488/3595 [============================>.] - ETA: 0s - loss: 1.3775 - accuracy: 0.5052 3595/3595 [==============================] - 2s 543us/sample - loss: 1.3797 - accuracy: 0.5057 - val_loss: 1.3055 - val_accuracy: 0.5284 Epoch 7/28 32/3595 [..............................] - ETA: 1s - loss: 1.3140 - accuracy: 0.5000 160/3595 [>.............................] - ETA: 1s - loss: 1.3474 - accuracy: 0.4875 256/3595 [=>............................] - ETA: 1s - loss: 1.3628 - accuracy: 0.5000 384/3595 [==>...........................] - ETA: 1s - loss: 1.3917 - accuracy: 0.4896 512/3595 [===>..........................] - ETA: 1s - loss: 1.4087 - accuracy: 0.4902 608/3595 [====>.........................] - ETA: 1s - loss: 1.3915 - accuracy: 0.5033 736/3595 [=====>........................] - ETA: 1s - loss: 1.3522 - accuracy: 0.5217 864/3595 [======>.......................] - ETA: 1s - loss: 1.3405 - accuracy: 0.5266 960/3595 [=======>......................] - ETA: 1s - loss: 1.3498 - accuracy: 0.5188 1088/3595 [========>.....................] - ETA: 1s - loss: 1.3461 - accuracy: 0.5184 1216/3595 [=========>....................] - ETA: 1s - loss: 1.3225 - accuracy: 0.5271 1344/3595 [==========>...................] - ETA: 1s - loss: 1.3085 - accuracy: 0.5320 1440/3595 [===========>..................] - ETA: 1s - loss: 1.3017 - accuracy: 0.5326 1568/3595 [============>.................] - ETA: 1s - loss: 1.3008 - accuracy: 0.5338 1696/3595 [=============>................] - ETA: 0s - loss: 1.3134 - accuracy: 0.5342 1824/3595 [==============>...............] - ETA: 0s - loss: 1.3114 - accuracy: 0.5318 1952/3595 [===============>..............] - ETA: 0s - loss: 1.3192 - accuracy: 0.5277 2048/3595 [================>.............] - ETA: 0s - loss: 1.3247 - accuracy: 0.5269 2176/3595 [=================>............] - ETA: 0s - loss: 1.3194 - accuracy: 0.5290 2304/3595 [==================>...........] - ETA: 0s - loss: 1.3138 - accuracy: 0.5317 2432/3595 [===================>..........] - ETA: 0s - loss: 1.3109 - accuracy: 0.5317 2560/3595 [====================>.........] - ETA: 0s - loss: 1.3102 - accuracy: 0.5324 2656/3595 [=====================>........] - ETA: 0s - loss: 1.3094 - accuracy: 0.5346 2784/3595 [======================>.......] - ETA: 0s - loss: 1.3121 - accuracy: 0.5338 2880/3595 [=======================>......] - ETA: 0s - loss: 1.3089 - accuracy: 0.5361 2976/3595 [=======================>......] - ETA: 0s - loss: 1.3072 - accuracy: 0.5356 3072/3595 [========================>.....] - ETA: 0s - loss: 1.3039 - accuracy: 0.5361 3200/3595 [=========================>....] - ETA: 0s - loss: 1.2979 - accuracy: 0.5391 3296/3595 [==========================>...] - ETA: 0s - loss: 1.2907 - accuracy: 0.5425 3424/3595 [===========================>..] - ETA: 0s - loss: 1.2907 - accuracy: 0.5397 3520/3595 [============================>.] - ETA: 0s - loss: 1.2966 - accuracy: 0.5372 3595/3595 [==============================] - 2s 569us/sample - loss: 1.2969 - accuracy: 0.5369 - val_loss: 1.2577 - val_accuracy: 0.5517 Epoch 8/28 32/3595 [..............................] - ETA: 1s - loss: 1.2448 - accuracy: 0.5312 128/3595 [>.............................] - ETA: 2s - loss: 1.2329 - accuracy: 0.5625 256/3595 [=>............................] - ETA: 1s - loss: 1.3137 - accuracy: 0.5469 384/3595 [==>...........................] - ETA: 1s - loss: 1.2676 - accuracy: 0.5599 512/3595 [===>..........................] - ETA: 1s - loss: 1.2641 - accuracy: 0.5547 640/3595 [====>.........................] - ETA: 1s - loss: 1.2478 - accuracy: 0.5531 768/3595 [=====>........................] - ETA: 1s - loss: 1.2454 - accuracy: 0.5560 896/3595 [======>.......................] - ETA: 1s - loss: 1.2512 - accuracy: 0.5513 992/3595 [=======>......................] - ETA: 1s - loss: 1.2482 - accuracy: 0.5565 1120/3595 [========>.....................] - ETA: 1s - loss: 1.2427 - accuracy: 0.5580 1248/3595 [=========>....................] - ETA: 1s - loss: 1.2368 - accuracy: 0.5633 1376/3595 [==========>...................] - ETA: 1s - loss: 1.2374 - accuracy: 0.5618 1504/3595 [===========>..................] - ETA: 1s - loss: 1.2447 - accuracy: 0.5592 1632/3595 [============>.................] - ETA: 1s - loss: 1.2492 - accuracy: 0.5582 1760/3595 [=============>................] - ETA: 0s - loss: 1.2432 - accuracy: 0.5580 1888/3595 [==============>...............] - ETA: 0s - loss: 1.2297 - accuracy: 0.5651 2016/3595 [===============>..............] - ETA: 0s - loss: 1.2318 - accuracy: 0.5640 2144/3595 [================>.............] - ETA: 0s - loss: 1.2280 - accuracy: 0.5676 2240/3595 [=================>............] - ETA: 0s - loss: 1.2279 - accuracy: 0.5683 2368/3595 [==================>...........] - ETA: 0s - loss: 1.2327 - accuracy: 0.5633 2496/3595 [===================>..........] - ETA: 0s - loss: 1.2400 - accuracy: 0.5621 2624/3595 [====================>.........] - ETA: 0s - loss: 1.2369 - accuracy: 0.5633 2720/3595 [=====================>........] - ETA: 0s - loss: 1.2413 - accuracy: 0.5636 2848/3595 [======================>.......] - ETA: 0s - loss: 1.2419 - accuracy: 0.5618 2976/3595 [=======================>......] - ETA: 0s - loss: 1.2413 - accuracy: 0.5598 3104/3595 [========================>.....] - ETA: 0s - loss: 1.2357 - accuracy: 0.5619 3232/3595 [=========================>....] - ETA: 0s - loss: 1.2332 - accuracy: 0.5628 3360/3595 [===========================>..] - ETA: 0s - loss: 1.2308 - accuracy: 0.5640 3488/3595 [============================>.] - ETA: 0s - loss: 1.2243 - accuracy: 0.5677 3584/3595 [============================>.] - ETA: 0s - loss: 1.2242 - accuracy: 0.5678 3595/3595 [==============================] - 2s 561us/sample - loss: 1.2235 - accuracy: 0.5677 - val_loss: 1.2110 - val_accuracy: 0.5695 Epoch 9/28 32/3595 [..............................] - ETA: 1s - loss: 1.4433 - accuracy: 0.4375 160/3595 [>.............................] - ETA: 1s - loss: 1.2850 - accuracy: 0.5188 288/3595 [=>............................] - ETA: 1s - loss: 1.1333 - accuracy: 0.5938 416/3595 [==>...........................] - ETA: 1s - loss: 1.1273 - accuracy: 0.5938 544/3595 [===>..........................] - ETA: 1s - loss: 1.0944 - accuracy: 0.6066 672/3595 [====>.........................] - ETA: 1s - loss: 1.1018 - accuracy: 0.6101 768/3595 [=====>........................] - ETA: 1s - loss: 1.1096 - accuracy: 0.6094 896/3595 [======>.......................] - ETA: 1s - loss: 1.1078 - accuracy: 0.6038 1024/3595 [=======>......................] - ETA: 1s - loss: 1.1270 - accuracy: 0.5918 1152/3595 [========>.....................] - ETA: 1s - loss: 1.1259 - accuracy: 0.5938 1280/3595 [=========>....................] - ETA: 1s - loss: 1.1271 - accuracy: 0.5938 1408/3595 [==========>...................] - ETA: 1s - loss: 1.1317 - accuracy: 0.5923 1536/3595 [===========>..................] - ETA: 1s - loss: 1.1313 - accuracy: 0.5964 1664/3595 [============>.................] - ETA: 0s - loss: 1.1261 - accuracy: 0.5998 1792/3595 [=============>................] - ETA: 0s - loss: 1.1199 - accuracy: 0.6049 1888/3595 [==============>...............] - ETA: 0s - loss: 1.1195 - accuracy: 0.6054 2016/3595 [===============>..............] - ETA: 0s - loss: 1.1229 - accuracy: 0.6007 2144/3595 [================>.............] - ETA: 0s - loss: 1.1301 - accuracy: 0.5984 2272/3595 [=================>............] - ETA: 0s - loss: 1.1347 - accuracy: 0.5968 2400/3595 [===================>..........] - ETA: 0s - loss: 1.1358 - accuracy: 0.5979 2528/3595 [====================>.........] - ETA: 0s - loss: 1.1469 - accuracy: 0.5949 2656/3595 [=====================>........] - ETA: 0s - loss: 1.1493 - accuracy: 0.5941 2784/3595 [======================>.......] - ETA: 0s - loss: 1.1458 - accuracy: 0.5948 2912/3595 [=======================>......] - ETA: 0s - loss: 1.1443 - accuracy: 0.5951 3040/3595 [========================>.....] - ETA: 0s - loss: 1.1500 - accuracy: 0.5938 3168/3595 [=========================>....] - ETA: 0s - loss: 1.1554 - accuracy: 0.5922 3296/3595 [==========================>...] - ETA: 0s - loss: 1.1575 - accuracy: 0.5913 3424/3595 [===========================>..] - ETA: 0s - loss: 1.1590 - accuracy: 0.5908 3552/3595 [============================>.] - ETA: 0s - loss: 1.1559 - accuracy: 0.5938 3595/3595 [==============================] - 2s 548us/sample - loss: 1.1574 - accuracy: 0.5928 - val_loss: 1.2191 - val_accuracy: 0.5706 Epoch 10/28 32/3595 [..............................] - ETA: 1s - loss: 1.1942 - accuracy: 0.5625 160/3595 [>.............................] - ETA: 1s - loss: 1.1681 - accuracy: 0.5875 256/3595 [=>............................] - ETA: 1s - loss: 1.1189 - accuracy: 0.5938 352/3595 [=>............................] - ETA: 1s - loss: 1.1578 - accuracy: 0.5881 480/3595 [===>..........................] - ETA: 1s - loss: 1.1643 - accuracy: 0.5792 608/3595 [====>.........................] - ETA: 1s - loss: 1.1459 - accuracy: 0.5757 736/3595 [=====>........................] - ETA: 1s - loss: 1.1341 - accuracy: 0.5910 864/3595 [======>.......................] - ETA: 1s - loss: 1.1159 - accuracy: 0.5984 992/3595 [=======>......................] - ETA: 1s - loss: 1.1134 - accuracy: 0.5988 1120/3595 [========>.....................] - ETA: 1s - loss: 1.1269 - accuracy: 0.5938 1216/3595 [=========>....................] - ETA: 1s - loss: 1.1239 - accuracy: 0.5987 1344/3595 [==========>...................] - ETA: 1s - loss: 1.1080 - accuracy: 0.6057 1472/3595 [===========>..................] - ETA: 1s - loss: 1.1080 - accuracy: 0.6033 1568/3595 [============>.................] - ETA: 1s - loss: 1.1178 - accuracy: 0.6008 1664/3595 [============>.................] - ETA: 1s - loss: 1.1140 - accuracy: 0.6022 1792/3595 [=============>................] - ETA: 0s - loss: 1.1114 - accuracy: 0.6060 1888/3595 [==============>...............] - ETA: 0s - loss: 1.1140 - accuracy: 0.6038 1984/3595 [===============>..............] - ETA: 0s - loss: 1.1091 - accuracy: 0.6069 2112/3595 [================>.............] - ETA: 0s - loss: 1.1107 - accuracy: 0.6042 2240/3595 [=================>............] - ETA: 0s - loss: 1.1139 - accuracy: 0.6040 2368/3595 [==================>...........] - ETA: 0s - loss: 1.1199 - accuracy: 0.6022 2496/3595 [===================>..........] - ETA: 0s - loss: 1.1241 - accuracy: 0.6046 2624/3595 [====================>.........] - ETA: 0s - loss: 1.1208 - accuracy: 0.6048 2752/3595 [=====================>........] - ETA: 0s - loss: 1.1278 - accuracy: 0.6017 2880/3595 [=======================>......] - ETA: 0s - loss: 1.1243 - accuracy: 0.6042 3008/3595 [========================>.....] - ETA: 0s - loss: 1.1212 - accuracy: 0.6054 3104/3595 [========================>.....] - ETA: 0s - loss: 1.1242 - accuracy: 0.6031 3232/3595 [=========================>....] - ETA: 0s - loss: 1.1175 - accuracy: 0.6049 3360/3595 [===========================>..] - ETA: 0s - loss: 1.1191 - accuracy: 0.6030 3488/3595 [============================>.] - ETA: 0s - loss: 1.1175 - accuracy: 0.6038 3595/3595 [==============================] - 2s 566us/sample - loss: 1.1139 - accuracy: 0.6047 - val_loss: 1.1652 - val_accuracy: 0.5851 Epoch 11/28 32/3595 [..............................] - ETA: 1s - loss: 1.1030 - accuracy: 0.6562 160/3595 [>.............................] - ETA: 1s - loss: 1.0832 - accuracy: 0.6187 288/3595 [=>............................] - ETA: 1s - loss: 1.0215 - accuracy: 0.6597 416/3595 [==>...........................] - ETA: 1s - loss: 1.0328 - accuracy: 0.6635 544/3595 [===>..........................] - ETA: 1s - loss: 1.0401 - accuracy: 0.6507 672/3595 [====>.........................] - ETA: 1s - loss: 1.0357 - accuracy: 0.6592 768/3595 [=====>........................] - ETA: 1s - loss: 1.0391 - accuracy: 0.6562 896/3595 [======>.......................] - ETA: 1s - loss: 1.0419 - accuracy: 0.6585 1024/3595 [=======>......................] - ETA: 1s - loss: 1.0571 - accuracy: 0.6543 1152/3595 [========>.....................] - ETA: 1s - loss: 1.0752 - accuracy: 0.6450 1280/3595 [=========>....................] - ETA: 1s - loss: 1.0651 - accuracy: 0.6469 1408/3595 [==========>...................] - ETA: 1s - loss: 1.0630 - accuracy: 0.6463 1536/3595 [===========>..................] - ETA: 1s - loss: 1.0681 - accuracy: 0.6432 1664/3595 [============>.................] - ETA: 0s - loss: 1.0666 - accuracy: 0.6388 1792/3595 [=============>................] - ETA: 0s - loss: 1.0739 - accuracy: 0.6378 1920/3595 [===============>..............] - ETA: 0s - loss: 1.0783 - accuracy: 0.6328 2048/3595 [================>.............] - ETA: 0s - loss: 1.0709 - accuracy: 0.6338 2176/3595 [=================>............] - ETA: 0s - loss: 1.0704 - accuracy: 0.6333 2272/3595 [=================>............] - ETA: 0s - loss: 1.0665 - accuracy: 0.6329 2400/3595 [===================>..........] - ETA: 0s - loss: 1.0645 - accuracy: 0.6317 2528/3595 [====================>.........] - ETA: 0s - loss: 1.0673 - accuracy: 0.6305 2656/3595 [=====================>........] - ETA: 0s - loss: 1.0704 - accuracy: 0.6288 2784/3595 [======================>.......] - ETA: 0s - loss: 1.0688 - accuracy: 0.6293 2912/3595 [=======================>......] - ETA: 0s - loss: 1.0752 - accuracy: 0.6250 3040/3595 [========================>.....] - ETA: 0s - loss: 1.0839 - accuracy: 0.6224 3168/3595 [=========================>....] - ETA: 0s - loss: 1.0846 - accuracy: 0.6222 3296/3595 [==========================>...] - ETA: 0s - loss: 1.0829 - accuracy: 0.6229 3424/3595 [===========================>..] - ETA: 0s - loss: 1.0810 - accuracy: 0.6238 3552/3595 [============================>.] - ETA: 0s - loss: 1.0789 - accuracy: 0.6242 3595/3595 [==============================] - 2s 543us/sample - loss: 1.0796 - accuracy: 0.6236 - val_loss: 1.1377 - val_accuracy: 0.5951 Epoch 12/28 32/3595 [..............................] - ETA: 1s - loss: 0.9850 - accuracy: 0.5938 160/3595 [>.............................] - ETA: 1s - loss: 0.9667 - accuracy: 0.6625 288/3595 [=>............................] - ETA: 1s - loss: 0.9966 - accuracy: 0.6667 416/3595 [==>...........................] - ETA: 1s - loss: 0.9530 - accuracy: 0.6827 544/3595 [===>..........................] - ETA: 1s - loss: 0.9849 - accuracy: 0.6765 640/3595 [====>.........................] - ETA: 1s - loss: 0.9786 - accuracy: 0.6703 768/3595 [=====>........................] - ETA: 1s - loss: 0.9869 - accuracy: 0.6732 896/3595 [======>.......................] - ETA: 1s - loss: 0.9896 - accuracy: 0.6708 1024/3595 [=======>......................] - ETA: 1s - loss: 0.9945 - accuracy: 0.6738 1120/3595 [========>.....................] - ETA: 1s - loss: 1.0054 - accuracy: 0.6696 1248/3595 [=========>....................] - ETA: 1s - loss: 1.0122 - accuracy: 0.6643 1376/3595 [==========>...................] - ETA: 1s - loss: 1.0053 - accuracy: 0.6628 1504/3595 [===========>..................] - ETA: 1s - loss: 1.0173 - accuracy: 0.6562 1600/3595 [============>.................] - ETA: 1s - loss: 1.0127 - accuracy: 0.6587 1728/3595 [=============>................] - ETA: 0s - loss: 1.0201 - accuracy: 0.6539 1856/3595 [==============>...............] - ETA: 0s - loss: 1.0119 - accuracy: 0.6541 1984/3595 [===============>..............] - ETA: 0s - loss: 1.0261 - accuracy: 0.6477 2080/3595 [================>.............] - ETA: 0s - loss: 1.0316 - accuracy: 0.6462 2208/3595 [=================>............] - ETA: 0s - loss: 1.0318 - accuracy: 0.6440 2336/3595 [==================>...........] - ETA: 0s - loss: 1.0364 - accuracy: 0.6430 2432/3595 [===================>..........] - ETA: 0s - loss: 1.0377 - accuracy: 0.6423 2560/3595 [====================>.........] - ETA: 0s - loss: 1.0417 - accuracy: 0.6395 2688/3595 [=====================>........] - ETA: 0s - loss: 1.0427 - accuracy: 0.6403 2816/3595 [======================>.......] - ETA: 0s - loss: 1.0468 - accuracy: 0.6399 2944/3595 [=======================>......] - ETA: 0s - loss: 1.0463 - accuracy: 0.6389 3040/3595 [========================>.....] - ETA: 0s - loss: 1.0451 - accuracy: 0.6385 3168/3595 [=========================>....] - ETA: 0s - loss: 1.0480 - accuracy: 0.6367 3296/3595 [==========================>...] - ETA: 0s - loss: 1.0441 - accuracy: 0.6383 3424/3595 [===========================>..] - ETA: 0s - loss: 1.0506 - accuracy: 0.6364 3552/3595 [============================>.] - ETA: 0s - loss: 1.0528 - accuracy: 0.6351 3595/3595 [==============================] - 2s 552us/sample - loss: 1.0520 - accuracy: 0.6359 - val_loss: 1.1283 - val_accuracy: 0.6029 Epoch 13/28 32/3595 [..............................] - ETA: 1s - loss: 0.6547 - accuracy: 0.7812 160/3595 [>.............................] - ETA: 1s - loss: 0.8675 - accuracy: 0.7375 256/3595 [=>............................] - ETA: 1s - loss: 0.9080 - accuracy: 0.7070 384/3595 [==>...........................] - ETA: 1s - loss: 0.9663 - accuracy: 0.6719 480/3595 [===>..........................] - ETA: 1s - loss: 0.9386 - accuracy: 0.6750 576/3595 [===>..........................] - ETA: 1s - loss: 0.9303 - accuracy: 0.6771 672/3595 [====>.........................] - ETA: 1s - loss: 0.9229 - accuracy: 0.6815 768/3595 [=====>........................] - ETA: 1s - loss: 0.9330 - accuracy: 0.6745 896/3595 [======>.......................] - ETA: 1s - loss: 0.9434 - accuracy: 0.6685 1024/3595 [=======>......................] - ETA: 1s - loss: 0.9772 - accuracy: 0.6543 1152/3595 [========>.....................] - ETA: 1s - loss: 0.9929 - accuracy: 0.6571 1280/3595 [=========>....................] - ETA: 1s - loss: 0.9905 - accuracy: 0.6570 1408/3595 [==========>...................] - ETA: 1s - loss: 1.0057 - accuracy: 0.6499 1504/3595 [===========>..................] - ETA: 1s - loss: 0.9977 - accuracy: 0.6569 1632/3595 [============>.................] - ETA: 1s - loss: 0.9976 - accuracy: 0.6581 1760/3595 [=============>................] - ETA: 1s - loss: 1.0000 - accuracy: 0.6551 1888/3595 [==============>...............] - ETA: 0s - loss: 1.0007 - accuracy: 0.6552 2016/3595 [===============>..............] - ETA: 0s - loss: 1.0047 - accuracy: 0.6548 2144/3595 [================>.............] - ETA: 0s - loss: 1.0034 - accuracy: 0.6544 2272/3595 [=================>............] - ETA: 0s - loss: 0.9960 - accuracy: 0.6576 2400/3595 [===================>..........] - ETA: 0s - loss: 0.9950 - accuracy: 0.6571 2528/3595 [====================>.........] - ETA: 0s - loss: 0.9915 - accuracy: 0.6574 2624/3595 [====================>.........] - ETA: 0s - loss: 0.9830 - accuracy: 0.6620 2752/3595 [=====================>........] - ETA: 0s - loss: 0.9832 - accuracy: 0.6613 2880/3595 [=======================>......] - ETA: 0s - loss: 0.9843 - accuracy: 0.6597 3008/3595 [========================>.....] - ETA: 0s - loss: 0.9838 - accuracy: 0.6586 3136/3595 [=========================>....] - ETA: 0s - loss: 0.9867 - accuracy: 0.6553 3264/3595 [==========================>...] - ETA: 0s - loss: 0.9844 - accuracy: 0.6547 3392/3595 [===========================>..] - ETA: 0s - loss: 0.9893 - accuracy: 0.6542 3520/3595 [============================>.] - ETA: 0s - loss: 0.9833 - accuracy: 0.6557 3595/3595 [==============================] - 2s 556us/sample - loss: 0.9798 - accuracy: 0.6567 - val_loss: 1.1134 - val_accuracy: 0.6040 Epoch 14/28 32/3595 [..............................] - ETA: 1s - loss: 0.7970 - accuracy: 0.6250 128/3595 [>.............................] - ETA: 2s - loss: 0.8042 - accuracy: 0.6719 256/3595 [=>............................] - ETA: 1s - loss: 0.8215 - accuracy: 0.7070 384/3595 [==>...........................] - ETA: 1s - loss: 0.8953 - accuracy: 0.6823 512/3595 [===>..........................] - ETA: 1s - loss: 0.9173 - accuracy: 0.6699 608/3595 [====>.........................] - ETA: 1s - loss: 0.8985 - accuracy: 0.6760 736/3595 [=====>........................] - ETA: 1s - loss: 0.9379 - accuracy: 0.6658 864/3595 [======>.......................] - ETA: 1s - loss: 0.9345 - accuracy: 0.6620 960/3595 [=======>......................] - ETA: 1s - loss: 0.9295 - accuracy: 0.6667 1088/3595 [========>.....................] - ETA: 1s - loss: 0.9367 - accuracy: 0.6673 1216/3595 [=========>....................] - ETA: 1s - loss: 0.9223 - accuracy: 0.6743 1344/3595 [==========>...................] - ETA: 1s - loss: 0.9202 - accuracy: 0.6741 1440/3595 [===========>..................] - ETA: 1s - loss: 0.9323 - accuracy: 0.6722 1568/3595 [============>.................] - ETA: 1s - loss: 0.9383 - accuracy: 0.6722 1696/3595 [=============>................] - ETA: 0s - loss: 0.9342 - accuracy: 0.6739 1824/3595 [==============>...............] - ETA: 0s - loss: 0.9438 - accuracy: 0.6700 1952/3595 [===============>..............] - ETA: 0s - loss: 0.9373 - accuracy: 0.6747 2080/3595 [================>.............] - ETA: 0s - loss: 0.9386 - accuracy: 0.6712 2176/3595 [=================>............] - ETA: 0s - loss: 0.9385 - accuracy: 0.6705 2304/3595 [==================>...........] - ETA: 0s - loss: 0.9380 - accuracy: 0.6710 2432/3595 [===================>..........] - ETA: 0s - loss: 0.9446 - accuracy: 0.6686 2560/3595 [====================>.........] - ETA: 0s - loss: 0.9458 - accuracy: 0.6684 2688/3595 [=====================>........] - ETA: 0s - loss: 0.9453 - accuracy: 0.6685 2816/3595 [======================>.......] - ETA: 0s - loss: 0.9455 - accuracy: 0.6683 2944/3595 [=======================>......] - ETA: 0s - loss: 0.9439 - accuracy: 0.6698 3072/3595 [========================>.....] - ETA: 0s - loss: 0.9500 - accuracy: 0.6660 3168/3595 [=========================>....] - ETA: 0s - loss: 0.9539 - accuracy: 0.6635 3296/3595 [==========================>...] - ETA: 0s - loss: 0.9561 - accuracy: 0.6635 3424/3595 [===========================>..] - ETA: 0s - loss: 0.9507 - accuracy: 0.6659 3552/3595 [============================>.] - ETA: 0s - loss: 0.9544 - accuracy: 0.6641 3595/3595 [==============================] - 2s 548us/sample - loss: 0.9559 - accuracy: 0.6651 - val_loss: 1.1079 - val_accuracy: 0.6051 Epoch 15/28 32/3595 [..............................] - ETA: 1s - loss: 0.7747 - accuracy: 0.7188 160/3595 [>.............................] - ETA: 1s - loss: 0.8027 - accuracy: 0.7312 288/3595 [=>............................] - ETA: 1s - loss: 0.8092 - accuracy: 0.7153 384/3595 [==>...........................] - ETA: 1s - loss: 0.8755 - accuracy: 0.6979 512/3595 [===>..........................] - ETA: 1s - loss: 0.8988 - accuracy: 0.6953 640/3595 [====>.........................] - ETA: 1s - loss: 0.9070 - accuracy: 0.6891 768/3595 [=====>........................] - ETA: 1s - loss: 0.8963 - accuracy: 0.6901 896/3595 [======>.......................] - ETA: 1s - loss: 0.9042 - accuracy: 0.6908 992/3595 [=======>......................] - ETA: 1s - loss: 0.9064 - accuracy: 0.6875 1120/3595 [========>.....................] - ETA: 1s - loss: 0.9109 - accuracy: 0.6839 1248/3595 [=========>....................] - ETA: 1s - loss: 0.9140 - accuracy: 0.6851 1376/3595 [==========>...................] - ETA: 1s - loss: 0.9175 - accuracy: 0.6846 1472/3595 [===========>..................] - ETA: 1s - loss: 0.9154 - accuracy: 0.6882 1600/3595 [============>.................] - ETA: 1s - loss: 0.9256 - accuracy: 0.6819 1728/3595 [=============>................] - ETA: 0s - loss: 0.9254 - accuracy: 0.6811 1856/3595 [==============>...............] - ETA: 0s - loss: 0.9199 - accuracy: 0.6805 1984/3595 [===============>..............] - ETA: 0s - loss: 0.9141 - accuracy: 0.6830 2112/3595 [================>.............] - ETA: 0s - loss: 0.9110 - accuracy: 0.6856 2240/3595 [=================>............] - ETA: 0s - loss: 0.9112 - accuracy: 0.6871 2368/3595 [==================>...........] - ETA: 0s - loss: 0.9147 - accuracy: 0.6875 2496/3595 [===================>..........] - ETA: 0s - loss: 0.9181 - accuracy: 0.6843 2624/3595 [====================>.........] - ETA: 0s - loss: 0.9174 - accuracy: 0.6837 2752/3595 [=====================>........] - ETA: 0s - loss: 0.9154 - accuracy: 0.6835 2880/3595 [=======================>......] - ETA: 0s - loss: 0.9156 - accuracy: 0.6833 3008/3595 [========================>.....] - ETA: 0s - loss: 0.9153 - accuracy: 0.6835 3104/3595 [========================>.....] - ETA: 0s - loss: 0.9134 - accuracy: 0.6833 3200/3595 [=========================>....] - ETA: 0s - loss: 0.9134 - accuracy: 0.6828 3296/3595 [==========================>...] - ETA: 0s - loss: 0.9164 - accuracy: 0.6826 3392/3595 [===========================>..] - ETA: 0s - loss: 0.9169 - accuracy: 0.6819 3488/3595 [============================>.] - ETA: 0s - loss: 0.9144 - accuracy: 0.6829 3584/3595 [============================>.] - ETA: 0s - loss: 0.9138 - accuracy: 0.6839 3595/3595 [==============================] - 2s 569us/sample - loss: 0.9159 - accuracy: 0.6829 - val_loss: 1.0837 - val_accuracy: 0.6162 Epoch 16/28 32/3595 [..............................] - ETA: 1s - loss: 0.7971 - accuracy: 0.7812 160/3595 [>.............................] - ETA: 1s - loss: 0.8350 - accuracy: 0.7125 288/3595 [=>............................] - ETA: 1s - loss: 0.8029 - accuracy: 0.7153 416/3595 [==>...........................] - ETA: 1s - loss: 0.8154 - accuracy: 0.7163 544/3595 [===>..........................] - ETA: 1s - loss: 0.8417 - accuracy: 0.6985 672/3595 [====>.........................] - ETA: 1s - loss: 0.8625 - accuracy: 0.6979 800/3595 [=====>........................] - ETA: 1s - loss: 0.8383 - accuracy: 0.7088 928/3595 [======>.......................] - ETA: 1s - loss: 0.8489 - accuracy: 0.7101 1056/3595 [=======>......................] - ETA: 1s - loss: 0.8648 - accuracy: 0.7055 1152/3595 [========>.....................] - ETA: 1s - loss: 0.8646 - accuracy: 0.7049 1280/3595 [=========>....................] - ETA: 1s - loss: 0.8638 - accuracy: 0.7039 1408/3595 [==========>...................] - ETA: 1s - loss: 0.8564 - accuracy: 0.7088 1536/3595 [===========>..................] - ETA: 1s - loss: 0.8601 - accuracy: 0.7103 1632/3595 [============>.................] - ETA: 1s - loss: 0.8557 - accuracy: 0.7126 1760/3595 [=============>................] - ETA: 0s - loss: 0.8471 - accuracy: 0.7142 1888/3595 [==============>...............] - ETA: 0s - loss: 0.8487 - accuracy: 0.7108 2016/3595 [===============>..............] - ETA: 0s - loss: 0.8508 - accuracy: 0.7088 2144/3595 [================>.............] - ETA: 0s - loss: 0.8479 - accuracy: 0.7085 2240/3595 [=================>............] - ETA: 0s - loss: 0.8504 - accuracy: 0.7063 2368/3595 [==================>...........] - ETA: 0s - loss: 0.8644 - accuracy: 0.7010 2496/3595 [===================>..........] - ETA: 0s - loss: 0.8695 - accuracy: 0.6987 2624/3595 [====================>.........] - ETA: 0s - loss: 0.8734 - accuracy: 0.6986 2752/3595 [=====================>........] - ETA: 0s - loss: 0.8747 - accuracy: 0.6962 2880/3595 [=======================>......] - ETA: 0s - loss: 0.8752 - accuracy: 0.6951 3008/3595 [========================>.....] - ETA: 0s - loss: 0.8728 - accuracy: 0.6958 3136/3595 [=========================>....] - ETA: 0s - loss: 0.8814 - accuracy: 0.6923 3264/3595 [==========================>...] - ETA: 0s - loss: 0.8802 - accuracy: 0.6936 3392/3595 [===========================>..] - ETA: 0s - loss: 0.8797 - accuracy: 0.6934 3520/3595 [============================>.] - ETA: 0s - loss: 0.8800 - accuracy: 0.6926 3595/3595 [==============================] - 2s 548us/sample - loss: 0.8835 - accuracy: 0.6907 - val_loss: 1.0434 - val_accuracy: 0.6240 Epoch 17/28 32/3595 [..............................] - ETA: 1s - loss: 0.6243 - accuracy: 0.8125 160/3595 [>.............................] - ETA: 1s - loss: 0.7318 - accuracy: 0.7625 288/3595 [=>............................] - ETA: 1s - loss: 0.8045 - accuracy: 0.7326 384/3595 [==>...........................] - ETA: 1s - loss: 0.8065 - accuracy: 0.7266 512/3595 [===>..........................] - ETA: 1s - loss: 0.8482 - accuracy: 0.7109 640/3595 [====>.........................] - ETA: 1s - loss: 0.8392 - accuracy: 0.7125 736/3595 [=====>........................] - ETA: 1s - loss: 0.8574 - accuracy: 0.7106 864/3595 [======>.......................] - ETA: 1s - loss: 0.8644 - accuracy: 0.7060 992/3595 [=======>......................] - ETA: 1s - loss: 0.8418 - accuracy: 0.7077 1088/3595 [========>.....................] - ETA: 1s - loss: 0.8322 - accuracy: 0.7105 1216/3595 [=========>....................] - ETA: 1s - loss: 0.8362 - accuracy: 0.7089 1344/3595 [==========>...................] - ETA: 1s - loss: 0.8390 - accuracy: 0.7054 1440/3595 [===========>..................] - ETA: 1s - loss: 0.8453 - accuracy: 0.7007 1568/3595 [============>.................] - ETA: 1s - loss: 0.8518 - accuracy: 0.6971 1696/3595 [=============>................] - ETA: 0s - loss: 0.8575 - accuracy: 0.6975 1824/3595 [==============>...............] - ETA: 0s - loss: 0.8600 - accuracy: 0.7001 1952/3595 [===============>..............] - ETA: 0s - loss: 0.8569 - accuracy: 0.7024 2080/3595 [================>.............] - ETA: 0s - loss: 0.8593 - accuracy: 0.7029 2208/3595 [=================>............] - ETA: 0s - loss: 0.8604 - accuracy: 0.7034 2336/3595 [==================>...........] - ETA: 0s - loss: 0.8588 - accuracy: 0.7012 2464/3595 [===================>..........] - ETA: 0s - loss: 0.8671 - accuracy: 0.6972 2592/3595 [====================>.........] - ETA: 0s - loss: 0.8633 - accuracy: 0.6971 2720/3595 [=====================>........] - ETA: 0s - loss: 0.8591 - accuracy: 0.6971 2848/3595 [======================>.......] - ETA: 0s - loss: 0.8579 - accuracy: 0.6973 2976/3595 [=======================>......] - ETA: 0s - loss: 0.8568 - accuracy: 0.6976 3072/3595 [========================>.....] - ETA: 0s - loss: 0.8558 - accuracy: 0.6979 3200/3595 [=========================>....] - ETA: 0s - loss: 0.8562 - accuracy: 0.6975 3328/3595 [==========================>...] - ETA: 0s - loss: 0.8627 - accuracy: 0.6965 3456/3595 [===========================>..] - ETA: 0s - loss: 0.8688 - accuracy: 0.6962 3584/3595 [============================>.] - ETA: 0s - loss: 0.8724 - accuracy: 0.6934 3595/3595 [==============================] - 2s 548us/sample - loss: 0.8731 - accuracy: 0.6929 - val_loss: 1.0587 - val_accuracy: 0.6196 Epoch 18/28 32/3595 [..............................] - ETA: 1s - loss: 0.8086 - accuracy: 0.7188 160/3595 [>.............................] - ETA: 1s - loss: 0.8358 - accuracy: 0.6875 256/3595 [=>............................] - ETA: 1s - loss: 0.8388 - accuracy: 0.7031 384/3595 [==>...........................] - ETA: 1s - loss: 0.8351 - accuracy: 0.7188 512/3595 [===>..........................] - ETA: 1s - loss: 0.8352 - accuracy: 0.7109 640/3595 [====>.........................] - ETA: 1s - loss: 0.8501 - accuracy: 0.6984 768/3595 [=====>........................] - ETA: 1s - loss: 0.8648 - accuracy: 0.6901 864/3595 [======>.......................] - ETA: 1s - loss: 0.8734 - accuracy: 0.6806 992/3595 [=======>......................] - ETA: 1s - loss: 0.8583 - accuracy: 0.6956 1120/3595 [========>.....................] - ETA: 1s - loss: 0.8519 - accuracy: 0.7018 1248/3595 [=========>....................] - ETA: 1s - loss: 0.8436 - accuracy: 0.7043 1376/3595 [==========>...................] - ETA: 1s - loss: 0.8199 - accuracy: 0.7137 1472/3595 [===========>..................] - ETA: 1s - loss: 0.8187 - accuracy: 0.7113 1600/3595 [============>.................] - ETA: 1s - loss: 0.8283 - accuracy: 0.7119 1728/3595 [=============>................] - ETA: 0s - loss: 0.8199 - accuracy: 0.7164 1824/3595 [==============>...............] - ETA: 0s - loss: 0.8260 - accuracy: 0.7144 1920/3595 [===============>..............] - ETA: 0s - loss: 0.8372 - accuracy: 0.7109 2016/3595 [===============>..............] - ETA: 0s - loss: 0.8389 - accuracy: 0.7088 2112/3595 [================>.............] - ETA: 0s - loss: 0.8374 - accuracy: 0.7083 2208/3595 [=================>............] - ETA: 0s - loss: 0.8389 - accuracy: 0.7088 2304/3595 [==================>...........] - ETA: 0s - loss: 0.8348 - accuracy: 0.7114 2432/3595 [===================>..........] - ETA: 0s - loss: 0.8354 - accuracy: 0.7081 2528/3595 [====================>.........] - ETA: 0s - loss: 0.8348 - accuracy: 0.7085 2656/3595 [=====================>........] - ETA: 0s - loss: 0.8327 - accuracy: 0.7105 2784/3595 [======================>.......] - ETA: 0s - loss: 0.8319 - accuracy: 0.7112 2912/3595 [=======================>......] - ETA: 0s - loss: 0.8310 - accuracy: 0.7112 3040/3595 [========================>.....] - ETA: 0s - loss: 0.8278 - accuracy: 0.7118 3168/3595 [=========================>....] - ETA: 0s - loss: 0.8220 - accuracy: 0.7131 3296/3595 [==========================>...] - ETA: 0s - loss: 0.8206 - accuracy: 0.7130 3424/3595 [===========================>..] - ETA: 0s - loss: 0.8235 - accuracy: 0.7103 3552/3595 [============================>.] - ETA: 0s - loss: 0.8218 - accuracy: 0.7123 3595/3595 [==============================] - 2s 565us/sample - loss: 0.8244 - accuracy: 0.7135 - val_loss: 1.0474 - val_accuracy: 0.6429 Epoch 19/28 32/3595 [..............................] - ETA: 1s - loss: 0.7403 - accuracy: 0.6250 160/3595 [>.............................] - ETA: 1s - loss: 0.7587 - accuracy: 0.7125 288/3595 [=>............................] - ETA: 1s - loss: 0.7835 - accuracy: 0.7326 384/3595 [==>...........................] - ETA: 1s - loss: 0.7880 - accuracy: 0.7448 512/3595 [===>..........................] - ETA: 1s - loss: 0.7994 - accuracy: 0.7344 640/3595 [====>.........................] - ETA: 1s - loss: 0.7791 - accuracy: 0.7422 768/3595 [=====>........................] - ETA: 1s - loss: 0.7957 - accuracy: 0.7331 864/3595 [======>.......................] - ETA: 1s - loss: 0.7840 - accuracy: 0.7396 992/3595 [=======>......................] - ETA: 1s - loss: 0.7989 - accuracy: 0.7319 1120/3595 [========>.....................] - ETA: 1s - loss: 0.8001 - accuracy: 0.7286 1248/3595 [=========>....................] - ETA: 1s - loss: 0.7980 - accuracy: 0.7300 1376/3595 [==========>...................] - ETA: 1s - loss: 0.7840 - accuracy: 0.7355 1504/3595 [===========>..................] - ETA: 1s - loss: 0.7871 - accuracy: 0.7340 1632/3595 [============>.................] - ETA: 1s - loss: 0.7769 - accuracy: 0.7414 1728/3595 [=============>................] - ETA: 0s - loss: 0.7825 - accuracy: 0.7378 1856/3595 [==============>...............] - ETA: 0s - loss: 0.7861 - accuracy: 0.7338 1984/3595 [===============>..............] - ETA: 0s - loss: 0.7916 - accuracy: 0.7324 2112/3595 [================>.............] - ETA: 0s - loss: 0.7845 - accuracy: 0.7344 2240/3595 [=================>............] - ETA: 0s - loss: 0.7871 - accuracy: 0.7348 2368/3595 [==================>...........] - ETA: 0s - loss: 0.7801 - accuracy: 0.7373 2464/3595 [===================>..........] - ETA: 0s - loss: 0.7813 - accuracy: 0.7374 2592/3595 [====================>.........] - ETA: 0s - loss: 0.7904 - accuracy: 0.7342 2720/3595 [=====================>........] - ETA: 0s - loss: 0.7846 - accuracy: 0.7357 2848/3595 [======================>.......] - ETA: 0s - loss: 0.7882 - accuracy: 0.7328 2976/3595 [=======================>......] - ETA: 0s - loss: 0.7830 - accuracy: 0.7345 3104/3595 [========================>.....] - ETA: 0s - loss: 0.7849 - accuracy: 0.7352 3232/3595 [=========================>....] - ETA: 0s - loss: 0.7910 - accuracy: 0.7314 3360/3595 [===========================>..] - ETA: 0s - loss: 0.7890 - accuracy: 0.7324 3456/3595 [===========================>..] - ETA: 0s - loss: 0.7980 - accuracy: 0.7289 3584/3595 [============================>.] - ETA: 0s - loss: 0.8047 - accuracy: 0.7266 3595/3595 [==============================] - 2s 543us/sample - loss: 0.8045 - accuracy: 0.7263 - val_loss: 1.0360 - val_accuracy: 0.6340 Epoch 20/28 32/3595 [..............................] - ETA: 3s - loss: 0.6438 - accuracy: 0.7188 160/3595 [>.............................] - ETA: 2s - loss: 0.7699 - accuracy: 0.7188 288/3595 [=>............................] - ETA: 1s - loss: 0.8258 - accuracy: 0.6979 416/3595 [==>...........................] - ETA: 1s - loss: 0.8154 - accuracy: 0.7067 512/3595 [===>..........................] - ETA: 1s - loss: 0.7931 - accuracy: 0.7227 640/3595 [====>.........................] - ETA: 1s - loss: 0.7915 - accuracy: 0.7219 768/3595 [=====>........................] - ETA: 1s - loss: 0.7684 - accuracy: 0.7383 896/3595 [======>.......................] - ETA: 1s - loss: 0.7616 - accuracy: 0.7400 1024/3595 [=======>......................] - ETA: 1s - loss: 0.7673 - accuracy: 0.7373 1152/3595 [========>.....................] - ETA: 1s - loss: 0.7599 - accuracy: 0.7431 1280/3595 [=========>....................] - ETA: 1s - loss: 0.7499 - accuracy: 0.7461 1376/3595 [==========>...................] - ETA: 1s - loss: 0.7504 - accuracy: 0.7471 1504/3595 [===========>..................] - ETA: 1s - loss: 0.7530 - accuracy: 0.7447 1632/3595 [============>.................] - ETA: 1s - loss: 0.7538 - accuracy: 0.7475 1760/3595 [=============>................] - ETA: 0s - loss: 0.7590 - accuracy: 0.7455 1888/3595 [==============>...............] - ETA: 0s - loss: 0.7551 - accuracy: 0.7495 1984/3595 [===============>..............] - ETA: 0s - loss: 0.7540 - accuracy: 0.7525 2112/3595 [================>.............] - ETA: 0s - loss: 0.7548 - accuracy: 0.7524 2240/3595 [=================>............] - ETA: 0s - loss: 0.7604 - accuracy: 0.7496 2368/3595 [==================>...........] - ETA: 0s - loss: 0.7587 - accuracy: 0.7479 2496/3595 [===================>..........] - ETA: 0s - loss: 0.7629 - accuracy: 0.7448 2592/3595 [====================>.........] - ETA: 0s - loss: 0.7682 - accuracy: 0.7450 2720/3595 [=====================>........] - ETA: 0s - loss: 0.7646 - accuracy: 0.7445 2848/3595 [======================>.......] - ETA: 0s - loss: 0.7654 - accuracy: 0.7426 2976/3595 [=======================>......] - ETA: 0s - loss: 0.7690 - accuracy: 0.7416 3104/3595 [========================>.....] - ETA: 0s - loss: 0.7711 - accuracy: 0.7410 3200/3595 [=========================>....] - ETA: 0s - loss: 0.7663 - accuracy: 0.7434 3328/3595 [==========================>...] - ETA: 0s - loss: 0.7684 - accuracy: 0.7437 3456/3595 [===========================>..] - ETA: 0s - loss: 0.7689 - accuracy: 0.7419 3584/3595 [============================>.] - ETA: 0s - loss: 0.7723 - accuracy: 0.7408 3595/3595 [==============================] - 2s 552us/sample - loss: 0.7719 - accuracy: 0.7408 - val_loss: 1.0307 - val_accuracy: 0.6329 Epoch 21/28 32/3595 [..............................] - ETA: 1s - loss: 0.5590 - accuracy: 0.8438 128/3595 [>.............................] - ETA: 2s - loss: 0.7654 - accuracy: 0.7109 256/3595 [=>............................] - ETA: 1s - loss: 0.7552 - accuracy: 0.7539 384/3595 [==>...........................] - ETA: 1s - loss: 0.7871 - accuracy: 0.7396 480/3595 [===>..........................] - ETA: 1s - loss: 0.7893 - accuracy: 0.7333 608/3595 [====>.........................] - ETA: 1s - loss: 0.7806 - accuracy: 0.7336 704/3595 [====>.........................] - ETA: 1s - loss: 0.7938 - accuracy: 0.7344 800/3595 [=====>........................] - ETA: 1s - loss: 0.7797 - accuracy: 0.7412 896/3595 [======>.......................] - ETA: 1s - loss: 0.7901 - accuracy: 0.7377 992/3595 [=======>......................] - ETA: 1s - loss: 0.7787 - accuracy: 0.7399 1088/3595 [========>.....................] - ETA: 1s - loss: 0.7781 - accuracy: 0.7417 1216/3595 [=========>....................] - ETA: 1s - loss: 0.7700 - accuracy: 0.7475 1344/3595 [==========>...................] - ETA: 1s - loss: 0.7639 - accuracy: 0.7478 1472/3595 [===========>..................] - ETA: 1s - loss: 0.7576 - accuracy: 0.7486 1600/3595 [============>.................] - ETA: 1s - loss: 0.7464 - accuracy: 0.7525 1728/3595 [=============>................] - ETA: 1s - loss: 0.7336 - accuracy: 0.7552 1856/3595 [==============>...............] - ETA: 0s - loss: 0.7314 - accuracy: 0.7559 1984/3595 [===============>..............] - ETA: 0s - loss: 0.7340 - accuracy: 0.7566 2112/3595 [================>.............] - ETA: 0s - loss: 0.7355 - accuracy: 0.7533 2208/3595 [=================>............] - ETA: 0s - loss: 0.7324 - accuracy: 0.7545 2336/3595 [==================>...........] - ETA: 0s - loss: 0.7364 - accuracy: 0.7534 2464/3595 [===================>..........] - ETA: 0s - loss: 0.7415 - accuracy: 0.7512 2592/3595 [====================>.........] - ETA: 0s - loss: 0.7410 - accuracy: 0.7515 2720/3595 [=====================>........] - ETA: 0s - loss: 0.7459 - accuracy: 0.7493 2848/3595 [======================>.......] - ETA: 0s - loss: 0.7448 - accuracy: 0.7461 2976/3595 [=======================>......] - ETA: 0s - loss: 0.7474 - accuracy: 0.7446 3104/3595 [========================>.....] - ETA: 0s - loss: 0.7472 - accuracy: 0.7461 3200/3595 [=========================>....] - ETA: 0s - loss: 0.7512 - accuracy: 0.7456 3328/3595 [==========================>...] - ETA: 0s - loss: 0.7534 - accuracy: 0.7446 3456/3595 [===========================>..] - ETA: 0s - loss: 0.7554 - accuracy: 0.7433 3584/3595 [============================>.] - ETA: 0s - loss: 0.7556 - accuracy: 0.7433 3595/3595 [==============================] - 2s 565us/sample - loss: 0.7568 - accuracy: 0.7433 - val_loss: 1.0023 - val_accuracy: 0.6507 Epoch 22/28 32/3595 [..............................] - ETA: 1s - loss: 0.4792 - accuracy: 0.8438 160/3595 [>.............................] - ETA: 1s - loss: 0.7120 - accuracy: 0.7750 256/3595 [=>............................] - ETA: 1s - loss: 0.7479 - accuracy: 0.7578 384/3595 [==>...........................] - ETA: 1s - loss: 0.7112 - accuracy: 0.7682 512/3595 [===>..........................] - ETA: 1s - loss: 0.7036 - accuracy: 0.7754 640/3595 [====>.........................] - ETA: 1s - loss: 0.7259 - accuracy: 0.7656 736/3595 [=====>........................] - ETA: 1s - loss: 0.7395 - accuracy: 0.7595 864/3595 [======>.......................] - ETA: 1s - loss: 0.7350 - accuracy: 0.7581 992/3595 [=======>......................] - ETA: 1s - loss: 0.7346 - accuracy: 0.7591 1120/3595 [========>.....................] - ETA: 1s - loss: 0.7166 - accuracy: 0.7652 1248/3595 [=========>....................] - ETA: 1s - loss: 0.7018 - accuracy: 0.7692 1376/3595 [==========>...................] - ETA: 1s - loss: 0.7029 - accuracy: 0.7674 1504/3595 [===========>..................] - ETA: 1s - loss: 0.7070 - accuracy: 0.7653 1632/3595 [============>.................] - ETA: 1s - loss: 0.7091 - accuracy: 0.7610 1760/3595 [=============>................] - ETA: 0s - loss: 0.7119 - accuracy: 0.7597 1888/3595 [==============>...............] - ETA: 0s - loss: 0.7064 - accuracy: 0.7617 2016/3595 [===============>..............] - ETA: 0s - loss: 0.7155 - accuracy: 0.7584 2112/3595 [================>.............] - ETA: 0s - loss: 0.7206 - accuracy: 0.7552 2240/3595 [=================>............] - ETA: 0s - loss: 0.7145 - accuracy: 0.7567 2368/3595 [==================>...........] - ETA: 0s - loss: 0.7160 - accuracy: 0.7559 2496/3595 [===================>..........] - ETA: 0s - loss: 0.7240 - accuracy: 0.7504 2624/3595 [====================>.........] - ETA: 0s - loss: 0.7287 - accuracy: 0.7489 2752/3595 [=====================>........] - ETA: 0s - loss: 0.7206 - accuracy: 0.7518 2848/3595 [======================>.......] - ETA: 0s - loss: 0.7171 - accuracy: 0.7532 2976/3595 [=======================>......] - ETA: 0s - loss: 0.7214 - accuracy: 0.7520 3104/3595 [========================>.....] - ETA: 0s - loss: 0.7142 - accuracy: 0.7561 3232/3595 [=========================>....] - ETA: 0s - loss: 0.7199 - accuracy: 0.7562 3360/3595 [===========================>..] - ETA: 0s - loss: 0.7203 - accuracy: 0.7554 3488/3595 [============================>.] - ETA: 0s - loss: 0.7188 - accuracy: 0.7549 3584/3595 [============================>.] - ETA: 0s - loss: 0.7166 - accuracy: 0.7559 3595/3595 [==============================] - 2s 543us/sample - loss: 0.7168 - accuracy: 0.7558 - val_loss: 1.0123 - val_accuracy: 0.6352 Epoch 23/28 32/3595 [..............................] - ETA: 1s - loss: 0.6847 - accuracy: 0.7188 160/3595 [>.............................] - ETA: 1s - loss: 0.8909 - accuracy: 0.6750 288/3595 [=>............................] - ETA: 1s - loss: 0.7681 - accuracy: 0.7153 384/3595 [==>...........................] - ETA: 1s - loss: 0.7371 - accuracy: 0.7266 512/3595 [===>..........................] - ETA: 1s - loss: 0.7319 - accuracy: 0.7324 640/3595 [====>.........................] - ETA: 1s - loss: 0.7220 - accuracy: 0.7531 768/3595 [=====>........................] - ETA: 1s - loss: 0.7454 - accuracy: 0.7396 896/3595 [======>.......................] - ETA: 1s - loss: 0.7365 - accuracy: 0.7467 1024/3595 [=======>......................] - ETA: 1s - loss: 0.7291 - accuracy: 0.7480 1152/3595 [========>.....................] - ETA: 1s - loss: 0.7259 - accuracy: 0.7483 1248/3595 [=========>....................] - ETA: 1s - loss: 0.7349 - accuracy: 0.7444 1376/3595 [==========>...................] - ETA: 1s - loss: 0.7375 - accuracy: 0.7413 1504/3595 [===========>..................] - ETA: 1s - loss: 0.7215 - accuracy: 0.7487 1600/3595 [============>.................] - ETA: 1s - loss: 0.7183 - accuracy: 0.7494 1728/3595 [=============>................] - ETA: 0s - loss: 0.7182 - accuracy: 0.7512 1856/3595 [==============>...............] - ETA: 0s - loss: 0.7128 - accuracy: 0.7527 1984/3595 [===============>..............] - ETA: 0s - loss: 0.7117 - accuracy: 0.7530 2080/3595 [================>.............] - ETA: 0s - loss: 0.7047 - accuracy: 0.7572 2208/3595 [=================>............] - ETA: 0s - loss: 0.7107 - accuracy: 0.7554 2336/3595 [==================>...........] - ETA: 0s - loss: 0.7073 - accuracy: 0.7573 2464/3595 [===================>..........] - ETA: 0s - loss: 0.6990 - accuracy: 0.7614 2592/3595 [====================>.........] - ETA: 0s - loss: 0.6992 - accuracy: 0.7604 2720/3595 [=====================>........] - ETA: 0s - loss: 0.7010 - accuracy: 0.7603 2848/3595 [======================>.......] - ETA: 0s - loss: 0.6973 - accuracy: 0.7630 2944/3595 [=======================>......] - ETA: 0s - loss: 0.6976 - accuracy: 0.7632 3072/3595 [========================>.....] - ETA: 0s - loss: 0.6957 - accuracy: 0.7624 3168/3595 [=========================>....] - ETA: 0s - loss: 0.6976 - accuracy: 0.7623 3296/3595 [==========================>...] - ETA: 0s - loss: 0.7023 - accuracy: 0.7618 3392/3595 [===========================>..] - ETA: 0s - loss: 0.7029 - accuracy: 0.7621 3488/3595 [============================>.] - ETA: 0s - loss: 0.7041 - accuracy: 0.7603 3584/3595 [============================>.] - ETA: 0s - loss: 0.7011 - accuracy: 0.7617 3595/3595 [==============================] - 2s 574us/sample - loss: 0.7025 - accuracy: 0.7613 - val_loss: 1.0003 - val_accuracy: 0.6474 Epoch 24/28 32/3595 [..............................] - ETA: 1s - loss: 0.7401 - accuracy: 0.7500 160/3595 [>.............................] - ETA: 1s - loss: 0.6941 - accuracy: 0.7563 288/3595 [=>............................] - ETA: 1s - loss: 0.6139 - accuracy: 0.7847 416/3595 [==>...........................] - ETA: 1s - loss: 0.6435 - accuracy: 0.7812 544/3595 [===>..........................] - ETA: 1s - loss: 0.6257 - accuracy: 0.7849 672/3595 [====>.........................] - ETA: 1s - loss: 0.6667 - accuracy: 0.7723 800/3595 [=====>........................] - ETA: 1s - loss: 0.6601 - accuracy: 0.7725 928/3595 [======>.......................] - ETA: 1s - loss: 0.6825 - accuracy: 0.7651 1056/3595 [=======>......................] - ETA: 1s - loss: 0.7058 - accuracy: 0.7585 1184/3595 [========>.....................] - ETA: 1s - loss: 0.7046 - accuracy: 0.7576 1312/3595 [=========>....................] - ETA: 1s - loss: 0.6944 - accuracy: 0.7622 1408/3595 [==========>...................] - ETA: 1s - loss: 0.6977 - accuracy: 0.7592 1536/3595 [===========>..................] - ETA: 1s - loss: 0.6848 - accuracy: 0.7643 1664/3595 [============>.................] - ETA: 0s - loss: 0.6832 - accuracy: 0.7656 1792/3595 [=============>................] - ETA: 0s - loss: 0.6825 - accuracy: 0.7667 1920/3595 [===============>..............] - ETA: 0s - loss: 0.6803 - accuracy: 0.7677 2048/3595 [================>.............] - ETA: 0s - loss: 0.6916 - accuracy: 0.7651 2176/3595 [=================>............] - ETA: 0s - loss: 0.6869 - accuracy: 0.7679 2304/3595 [==================>...........] - ETA: 0s - loss: 0.6856 - accuracy: 0.7665 2432/3595 [===================>..........] - ETA: 0s - loss: 0.6826 - accuracy: 0.7669 2560/3595 [====================>.........] - ETA: 0s - loss: 0.6823 - accuracy: 0.7676 2688/3595 [=====================>........] - ETA: 0s - loss: 0.6826 - accuracy: 0.7671 2816/3595 [======================>.......] - ETA: 0s - loss: 0.6831 - accuracy: 0.7663 2912/3595 [=======================>......] - ETA: 0s - loss: 0.6868 - accuracy: 0.7641 3040/3595 [========================>.....] - ETA: 0s - loss: 0.6902 - accuracy: 0.7622 3168/3595 [=========================>....] - ETA: 0s - loss: 0.6935 - accuracy: 0.7614 3296/3595 [==========================>...] - ETA: 0s - loss: 0.6934 - accuracy: 0.7621 3424/3595 [===========================>..] - ETA: 0s - loss: 0.6961 - accuracy: 0.7623 3552/3595 [============================>.] - ETA: 0s - loss: 0.6934 - accuracy: 0.7632 3595/3595 [==============================] - 2s 530us/sample - loss: 0.6957 - accuracy: 0.7633 - val_loss: 1.0047 - val_accuracy: 0.6407 Epoch 25/28 32/3595 [..............................] - ETA: 1s - loss: 0.8445 - accuracy: 0.7188 160/3595 [>.............................] - ETA: 2s - loss: 0.8176 - accuracy: 0.6875 288/3595 [=>............................] - ETA: 1s - loss: 0.7815 - accuracy: 0.6944 416/3595 [==>...........................] - ETA: 1s - loss: 0.7881 - accuracy: 0.7091 544/3595 [===>..........................] - ETA: 1s - loss: 0.7545 - accuracy: 0.7243 640/3595 [====>.........................] - ETA: 1s - loss: 0.7673 - accuracy: 0.7297 768/3595 [=====>........................] - ETA: 1s - loss: 0.7467 - accuracy: 0.7422 896/3595 [======>.......................] - ETA: 1s - loss: 0.7161 - accuracy: 0.7578 1024/3595 [=======>......................] - ETA: 1s - loss: 0.7302 - accuracy: 0.7559 1120/3595 [========>.....................] - ETA: 1s - loss: 0.7240 - accuracy: 0.7589 1248/3595 [=========>....................] - ETA: 1s - loss: 0.7143 - accuracy: 0.7612 1376/3595 [==========>...................] - ETA: 1s - loss: 0.6998 - accuracy: 0.7689 1504/3595 [===========>..................] - ETA: 1s - loss: 0.6929 - accuracy: 0.7713 1632/3595 [============>.................] - ETA: 1s - loss: 0.6866 - accuracy: 0.7721 1760/3595 [=============>................] - ETA: 0s - loss: 0.6833 - accuracy: 0.7739 1856/3595 [==============>...............] - ETA: 0s - loss: 0.6831 - accuracy: 0.7716 1984/3595 [===============>..............] - ETA: 0s - loss: 0.6880 - accuracy: 0.7697 2080/3595 [================>.............] - ETA: 0s - loss: 0.6891 - accuracy: 0.7702 2208/3595 [=================>............] - ETA: 0s - loss: 0.6925 - accuracy: 0.7672 2304/3595 [==================>...........] - ETA: 0s - loss: 0.6847 - accuracy: 0.7700 2400/3595 [===================>..........] - ETA: 0s - loss: 0.6762 - accuracy: 0.7750 2528/3595 [====================>.........] - ETA: 0s - loss: 0.6764 - accuracy: 0.7749 2624/3595 [====================>.........] - ETA: 0s - loss: 0.6758 - accuracy: 0.7732 2752/3595 [=====================>........] - ETA: 0s - loss: 0.6825 - accuracy: 0.7703 2848/3595 [======================>.......] - ETA: 0s - loss: 0.6778 - accuracy: 0.7714 2976/3595 [=======================>......] - ETA: 0s - loss: 0.6767 - accuracy: 0.7728 3104/3595 [========================>.....] - ETA: 0s - loss: 0.6764 - accuracy: 0.7732 3232/3595 [=========================>....] - ETA: 0s - loss: 0.6781 - accuracy: 0.7717 3360/3595 [===========================>..] - ETA: 0s - loss: 0.6796 - accuracy: 0.7702 3456/3595 [===========================>..] - ETA: 0s - loss: 0.6818 - accuracy: 0.7691 3584/3595 [============================>.] - ETA: 0s - loss: 0.6808 - accuracy: 0.7693 3595/3595 [==============================] - 2s 565us/sample - loss: 0.6823 - accuracy: 0.7688 - val_loss: 0.9964 - val_accuracy: 0.6496 Epoch 26/28 32/3595 [..............................] - ETA: 1s - loss: 0.6174 - accuracy: 0.7812 160/3595 [>.............................] - ETA: 1s - loss: 0.7471 - accuracy: 0.7375 288/3595 [=>............................] - ETA: 1s - loss: 0.6255 - accuracy: 0.7778 384/3595 [==>...........................] - ETA: 1s - loss: 0.6140 - accuracy: 0.7734 512/3595 [===>..........................] - ETA: 1s - loss: 0.6471 - accuracy: 0.7637 640/3595 [====>.........................] - ETA: 1s - loss: 0.6428 - accuracy: 0.7688 768/3595 [=====>........................] - ETA: 1s - loss: 0.6443 - accuracy: 0.7708 896/3595 [======>.......................] - ETA: 1s - loss: 0.6335 - accuracy: 0.7835 1024/3595 [=======>......................] - ETA: 1s - loss: 0.6473 - accuracy: 0.7812 1120/3595 [========>.....................] - ETA: 1s - loss: 0.6317 - accuracy: 0.7884 1248/3595 [=========>....................] - ETA: 1s - loss: 0.6417 - accuracy: 0.7845 1376/3595 [==========>...................] - ETA: 1s - loss: 0.6362 - accuracy: 0.7849 1504/3595 [===========>..................] - ETA: 1s - loss: 0.6437 - accuracy: 0.7793 1600/3595 [============>.................] - ETA: 1s - loss: 0.6441 - accuracy: 0.7788 1728/3595 [=============>................] - ETA: 0s - loss: 0.6479 - accuracy: 0.7755 1856/3595 [==============>...............] - ETA: 0s - loss: 0.6462 - accuracy: 0.7769 1952/3595 [===============>..............] - ETA: 0s - loss: 0.6488 - accuracy: 0.7792 2048/3595 [================>.............] - ETA: 0s - loss: 0.6519 - accuracy: 0.7769 2144/3595 [================>.............] - ETA: 0s - loss: 0.6493 - accuracy: 0.7785 2240/3595 [=================>............] - ETA: 0s - loss: 0.6531 - accuracy: 0.7804 2336/3595 [==================>...........] - ETA: 0s - loss: 0.6527 - accuracy: 0.7804 2432/3595 [===================>..........] - ETA: 0s - loss: 0.6467 - accuracy: 0.7817 2528/3595 [====================>.........] - ETA: 0s - loss: 0.6417 - accuracy: 0.7836 2656/3595 [=====================>........] - ETA: 0s - loss: 0.6422 - accuracy: 0.7846 2784/3595 [======================>.......] - ETA: 0s - loss: 0.6470 - accuracy: 0.7830 2912/3595 [=======================>......] - ETA: 0s - loss: 0.6445 - accuracy: 0.7837 3008/3595 [========================>.....] - ETA: 0s - loss: 0.6461 - accuracy: 0.7842 3136/3595 [=========================>....] - ETA: 0s - loss: 0.6489 - accuracy: 0.7832 3264/3595 [==========================>...] - ETA: 0s - loss: 0.6471 - accuracy: 0.7840 3392/3595 [===========================>..] - ETA: 0s - loss: 0.6519 - accuracy: 0.7824 3520/3595 [============================>.] - ETA: 0s - loss: 0.6486 - accuracy: 0.7821 3595/3595 [==============================] - 2s 572us/sample - loss: 0.6486 - accuracy: 0.7830 - val_loss: 0.9941 - val_accuracy: 0.6429 Epoch 27/28 32/3595 [..............................] - ETA: 1s - loss: 0.8839 - accuracy: 0.6562 160/3595 [>.............................] - ETA: 1s - loss: 0.7047 - accuracy: 0.7563 288/3595 [=>............................] - ETA: 1s - loss: 0.6352 - accuracy: 0.7882 416/3595 [==>...........................] - ETA: 1s - loss: 0.6470 - accuracy: 0.7740 544/3595 [===>..........................] - ETA: 1s - loss: 0.6096 - accuracy: 0.7996 672/3595 [====>.........................] - ETA: 1s - loss: 0.6156 - accuracy: 0.7917 800/3595 [=====>........................] - ETA: 1s - loss: 0.6083 - accuracy: 0.7975 928/3595 [======>.......................] - ETA: 1s - loss: 0.5951 - accuracy: 0.7996 1056/3595 [=======>......................] - ETA: 1s - loss: 0.5878 - accuracy: 0.7983 1152/3595 [========>.....................] - ETA: 1s - loss: 0.6028 - accuracy: 0.7943 1280/3595 [=========>....................] - ETA: 1s - loss: 0.6045 - accuracy: 0.7953 1408/3595 [==========>...................] - ETA: 1s - loss: 0.6051 - accuracy: 0.7919 1536/3595 [===========>..................] - ETA: 1s - loss: 0.6059 - accuracy: 0.7962 1664/3595 [============>.................] - ETA: 0s - loss: 0.6151 - accuracy: 0.7927 1760/3595 [=============>................] - ETA: 0s - loss: 0.6183 - accuracy: 0.7926 1888/3595 [==============>...............] - ETA: 0s - loss: 0.6200 - accuracy: 0.7918 2016/3595 [===============>..............] - ETA: 0s - loss: 0.6204 - accuracy: 0.7907 2144/3595 [================>.............] - ETA: 0s - loss: 0.6198 - accuracy: 0.7915 2272/3595 [=================>............] - ETA: 0s - loss: 0.6249 - accuracy: 0.7879 2368/3595 [==================>...........] - ETA: 0s - loss: 0.6251 - accuracy: 0.7872 2496/3595 [===================>..........] - ETA: 0s - loss: 0.6242 - accuracy: 0.7869 2624/3595 [====================>.........] - ETA: 0s - loss: 0.6287 - accuracy: 0.7843 2752/3595 [=====================>........] - ETA: 0s - loss: 0.6299 - accuracy: 0.7834 2880/3595 [=======================>......] - ETA: 0s - loss: 0.6284 - accuracy: 0.7840 3008/3595 [========================>.....] - ETA: 0s - loss: 0.6252 - accuracy: 0.7852 3136/3595 [=========================>....] - ETA: 0s - loss: 0.6277 - accuracy: 0.7848 3264/3595 [==========================>...] - ETA: 0s - loss: 0.6298 - accuracy: 0.7846 3392/3595 [===========================>..] - ETA: 0s - loss: 0.6347 - accuracy: 0.7827 3520/3595 [============================>.] - ETA: 0s - loss: 0.6330 - accuracy: 0.7835 3595/3595 [==============================] - 2s 548us/sample - loss: 0.6331 - accuracy: 0.7833 - val_loss: 0.9943 - val_accuracy: 0.6563 Epoch 28/28 32/3595 [..............................] - ETA: 1s - loss: 0.4441 - accuracy: 0.8750 160/3595 [>.............................] - ETA: 1s - loss: 0.5634 - accuracy: 0.8125 256/3595 [=>............................] - ETA: 1s - loss: 0.6020 - accuracy: 0.8086 384/3595 [==>...........................] - ETA: 1s - loss: 0.6063 - accuracy: 0.8021 512/3595 [===>..........................] - ETA: 1s - loss: 0.5946 - accuracy: 0.8047 608/3595 [====>.........................] - ETA: 1s - loss: 0.5972 - accuracy: 0.7977 736/3595 [=====>........................] - ETA: 1s - loss: 0.6045 - accuracy: 0.7894 864/3595 [======>.......................] - ETA: 1s - loss: 0.6136 - accuracy: 0.7870 992/3595 [=======>......................] - ETA: 1s - loss: 0.6130 - accuracy: 0.7873 1120/3595 [========>.....................] - ETA: 1s - loss: 0.6047 - accuracy: 0.7902 1216/3595 [=========>....................] - ETA: 1s - loss: 0.6122 - accuracy: 0.7903 1344/3595 [==========>...................] - ETA: 1s - loss: 0.6119 - accuracy: 0.7909 1472/3595 [===========>..................] - ETA: 1s - loss: 0.6114 - accuracy: 0.7914 1600/3595 [============>.................] - ETA: 1s - loss: 0.6090 - accuracy: 0.7931 1728/3595 [=============>................] - ETA: 0s - loss: 0.6109 - accuracy: 0.7870 1856/3595 [==============>...............] - ETA: 0s - loss: 0.6076 - accuracy: 0.7866 1984/3595 [===============>..............] - ETA: 0s - loss: 0.6063 - accuracy: 0.7888 2080/3595 [================>.............] - ETA: 0s - loss: 0.6034 - accuracy: 0.7923 2208/3595 [=================>............] - ETA: 0s - loss: 0.6075 - accuracy: 0.7899 2336/3595 [==================>...........] - ETA: 0s - loss: 0.6056 - accuracy: 0.7902 2464/3595 [===================>..........] - ETA: 0s - loss: 0.6050 - accuracy: 0.7906 2592/3595 [====================>.........] - ETA: 0s - loss: 0.6030 - accuracy: 0.7924 2720/3595 [=====================>........] - ETA: 0s - loss: 0.6048 - accuracy: 0.7945 2848/3595 [======================>.......] - ETA: 0s - loss: 0.6043 - accuracy: 0.7932 2976/3595 [=======================>......] - ETA: 0s - loss: 0.6012 - accuracy: 0.7947 3104/3595 [========================>.....] - ETA: 0s - loss: 0.6013 - accuracy: 0.7935 3232/3595 [=========================>....] - ETA: 0s - loss: 0.6030 - accuracy: 0.7936 3360/3595 [===========================>..] - ETA: 0s - loss: 0.6054 - accuracy: 0.7926 3456/3595 [===========================>..] - ETA: 0s - loss: 0.6049 - accuracy: 0.7920 3584/3595 [============================>.] - ETA: 0s - loss: 0.6056 - accuracy: 0.7919 3595/3595 [==============================] - 2s 549us/sample - loss: 0.6050 - accuracy: 0.7925 - val_loss: 0.9775 - val_accuracy: 0.6563 Evaluating model for iteration 3... 1498/1498 - 0s - loss: 0.9487 - accuracy: 0.6696 Accuracy for iteration 3 0.6695594191551208 Training model for iteration 4... Train on 3595 samples, validate on 899 samples Epoch 1/28 32/3595 [..............................] - ETA: 53s - loss: 3.6652 - accuracy: 0.0625 128/3595 [>.............................] - ETA: 14s - loss: 3.1650 - accuracy: 0.0781 256/3595 [=>............................] - ETA: 7s - loss: 3.0226 - accuracy: 0.1250 384/3595 [==>...........................] - ETA: 5s - loss: 3.1248 - accuracy: 0.1250 480/3595 [===>..........................] - ETA: 4s - loss: 3.1012 - accuracy: 0.1208 608/3595 [====>.........................] - ETA: 3s - loss: 3.0522 - accuracy: 0.1201 736/3595 [=====>........................] - ETA: 3s - loss: 3.0368 - accuracy: 0.1155 864/3595 [======>.......................] - ETA: 2s - loss: 2.9918 - accuracy: 0.1296 992/3595 [=======>......................] - ETA: 2s - loss: 2.9470 - accuracy: 0.1361 1120/3595 [========>.....................] - ETA: 2s - loss: 2.9506 - accuracy: 0.1357 1216/3595 [=========>....................] - ETA: 2s - loss: 2.8986 - accuracy: 0.1431 1344/3595 [==========>...................] - ETA: 1s - loss: 2.8716 - accuracy: 0.1510 1472/3595 [===========>..................] - ETA: 1s - loss: 2.8364 - accuracy: 0.1576 1600/3595 [============>.................] - ETA: 1s - loss: 2.8110 - accuracy: 0.1619 1696/3595 [=============>................] - ETA: 1s - loss: 2.7928 - accuracy: 0.1657 1824/3595 [==============>...............] - ETA: 1s - loss: 2.7803 - accuracy: 0.1683 1952/3595 [===============>..............] - ETA: 1s - loss: 2.7478 - accuracy: 0.1732 2048/3595 [================>.............] - ETA: 1s - loss: 2.7372 - accuracy: 0.1738 2176/3595 [=================>............] - ETA: 1s - loss: 2.7263 - accuracy: 0.1737 2304/3595 [==================>...........] - ETA: 0s - loss: 2.7075 - accuracy: 0.1762 2400/3595 [===================>..........] - ETA: 0s - loss: 2.6902 - accuracy: 0.1800 2528/3595 [====================>.........] - ETA: 0s - loss: 2.6632 - accuracy: 0.1879 2656/3595 [=====================>........] - ETA: 0s - loss: 2.6511 - accuracy: 0.1886 2784/3595 [======================>.......] - ETA: 0s - loss: 2.6473 - accuracy: 0.1897 2912/3595 [=======================>......] - ETA: 0s - loss: 2.6183 - accuracy: 0.1954 3040/3595 [========================>.....] - ETA: 0s - loss: 2.6002 - accuracy: 0.1993 3168/3595 [=========================>....] - ETA: 0s - loss: 2.5902 - accuracy: 0.2036 3296/3595 [==========================>...] - ETA: 0s - loss: 2.5807 - accuracy: 0.2054 3424/3595 [===========================>..] - ETA: 0s - loss: 2.5670 - accuracy: 0.2097 3552/3595 [============================>.] - ETA: 0s - loss: 2.5526 - accuracy: 0.2128 3595/3595 [==============================] - 3s 826us/sample - loss: 2.5520 - accuracy: 0.2131 - val_loss: 2.1275 - val_accuracy: 0.2636 Epoch 2/28 32/3595 [..............................] - ETA: 1s - loss: 2.0565 - accuracy: 0.3438 128/3595 [>.............................] - ETA: 2s - loss: 2.2544 - accuracy: 0.2891 256/3595 [=>............................] - ETA: 1s - loss: 2.1948 - accuracy: 0.2852 384/3595 [==>...........................] - ETA: 1s - loss: 2.1428 - accuracy: 0.3047 480/3595 [===>..........................] - ETA: 1s - loss: 2.1138 - accuracy: 0.3063 608/3595 [====>.........................] - ETA: 1s - loss: 2.1039 - accuracy: 0.3125 736/3595 [=====>........................] - ETA: 1s - loss: 2.1070 - accuracy: 0.3111 832/3595 [=====>........................] - ETA: 1s - loss: 2.0911 - accuracy: 0.3161 960/3595 [=======>......................] - ETA: 1s - loss: 2.0809 - accuracy: 0.3177 1056/3595 [=======>......................] - ETA: 1s - loss: 2.0667 - accuracy: 0.3191 1184/3595 [========>.....................] - ETA: 1s - loss: 2.0635 - accuracy: 0.3184 1280/3595 [=========>....................] - ETA: 1s - loss: 2.0550 - accuracy: 0.3219 1376/3595 [==========>...................] - ETA: 1s - loss: 2.0815 - accuracy: 0.3169 1472/3595 [===========>..................] - ETA: 1s - loss: 2.0694 - accuracy: 0.3200 1600/3595 [============>.................] - ETA: 1s - loss: 2.0557 - accuracy: 0.3212 1728/3595 [=============>................] - ETA: 1s - loss: 2.0498 - accuracy: 0.3212 1824/3595 [==============>...............] - ETA: 1s - loss: 2.0518 - accuracy: 0.3196 1952/3595 [===============>..............] - ETA: 0s - loss: 2.0362 - accuracy: 0.3243 2080/3595 [================>.............] - ETA: 0s - loss: 2.0410 - accuracy: 0.3236 2208/3595 [=================>............] - ETA: 0s - loss: 2.0288 - accuracy: 0.3261 2336/3595 [==================>...........] - ETA: 0s - loss: 2.0316 - accuracy: 0.3249 2464/3595 [===================>..........] - ETA: 0s - loss: 2.0215 - accuracy: 0.3275 2592/3595 [====================>.........] - ETA: 0s - loss: 2.0220 - accuracy: 0.3275 2688/3595 [=====================>........] - ETA: 0s - loss: 2.0216 - accuracy: 0.3270 2816/3595 [======================>.......] - ETA: 0s - loss: 2.0262 - accuracy: 0.3267 2944/3595 [=======================>......] - ETA: 0s - loss: 2.0187 - accuracy: 0.3268 3072/3595 [========================>.....] - ETA: 0s - loss: 2.0146 - accuracy: 0.3275 3200/3595 [=========================>....] - ETA: 0s - loss: 2.0101 - accuracy: 0.3316 3328/3595 [==========================>...] - ETA: 0s - loss: 2.0058 - accuracy: 0.3308 3456/3595 [===========================>..] - ETA: 0s - loss: 1.9999 - accuracy: 0.3325 3584/3595 [============================>.] - ETA: 0s - loss: 1.9953 - accuracy: 0.3340 3595/3595 [==============================] - 2s 565us/sample - loss: 1.9960 - accuracy: 0.3332 - val_loss: 1.7509 - val_accuracy: 0.3949 Epoch 3/28 32/3595 [..............................] - ETA: 1s - loss: 1.9015 - accuracy: 0.3438 128/3595 [>.............................] - ETA: 2s - loss: 1.8459 - accuracy: 0.3672 256/3595 [=>............................] - ETA: 1s - loss: 1.7564 - accuracy: 0.4023 384/3595 [==>...........................] - ETA: 1s - loss: 1.7411 - accuracy: 0.4167 512/3595 [===>..........................] - ETA: 1s - loss: 1.7810 - accuracy: 0.4023 640/3595 [====>.........................] - ETA: 1s - loss: 1.7535 - accuracy: 0.4016 768/3595 [=====>........................] - ETA: 1s - loss: 1.7539 - accuracy: 0.3945 896/3595 [======>.......................] - ETA: 1s - loss: 1.7545 - accuracy: 0.3929 992/3595 [=======>......................] - ETA: 1s - loss: 1.7509 - accuracy: 0.3942 1120/3595 [========>.....................] - ETA: 1s - loss: 1.7458 - accuracy: 0.3929 1248/3595 [=========>....................] - ETA: 1s - loss: 1.7384 - accuracy: 0.3942 1376/3595 [==========>...................] - ETA: 1s - loss: 1.7487 - accuracy: 0.3852 1472/3595 [===========>..................] - ETA: 1s - loss: 1.7643 - accuracy: 0.3832 1600/3595 [============>.................] - ETA: 1s - loss: 1.7725 - accuracy: 0.3806 1728/3595 [=============>................] - ETA: 0s - loss: 1.7770 - accuracy: 0.3802 1856/3595 [==============>...............] - ETA: 0s - loss: 1.7816 - accuracy: 0.3782 1984/3595 [===============>..............] - ETA: 0s - loss: 1.7794 - accuracy: 0.3785 2112/3595 [================>.............] - ETA: 0s - loss: 1.7796 - accuracy: 0.3783 2240/3595 [=================>............] - ETA: 0s - loss: 1.7715 - accuracy: 0.3786 2368/3595 [==================>...........] - ETA: 0s - loss: 1.7688 - accuracy: 0.3796 2496/3595 [===================>..........] - ETA: 0s - loss: 1.7624 - accuracy: 0.3814 2624/3595 [====================>.........] - ETA: 0s - loss: 1.7580 - accuracy: 0.3834 2720/3595 [=====================>........] - ETA: 0s - loss: 1.7640 - accuracy: 0.3816 2848/3595 [======================>.......] - ETA: 0s - loss: 1.7621 - accuracy: 0.3817 2976/3595 [=======================>......] - ETA: 0s - loss: 1.7531 - accuracy: 0.3868 3104/3595 [========================>.....] - ETA: 0s - loss: 1.7546 - accuracy: 0.3876 3232/3595 [=========================>....] - ETA: 0s - loss: 1.7518 - accuracy: 0.3868 3360/3595 [===========================>..] - ETA: 0s - loss: 1.7494 - accuracy: 0.3854 3488/3595 [============================>.] - ETA: 0s - loss: 1.7499 - accuracy: 0.3859 3584/3595 [============================>.] - ETA: 0s - loss: 1.7465 - accuracy: 0.3864 3595/3595 [==============================] - 2s 561us/sample - loss: 1.7470 - accuracy: 0.3861 - val_loss: 1.5638 - val_accuracy: 0.4338 Epoch 4/28 32/3595 [..............................] - ETA: 1s - loss: 1.6535 - accuracy: 0.3750 160/3595 [>.............................] - ETA: 1s - loss: 1.5855 - accuracy: 0.4500 256/3595 [=>............................] - ETA: 1s - loss: 1.6453 - accuracy: 0.4258 384/3595 [==>...........................] - ETA: 1s - loss: 1.5441 - accuracy: 0.4531 512/3595 [===>..........................] - ETA: 1s - loss: 1.5473 - accuracy: 0.4492 640/3595 [====>.........................] - ETA: 1s - loss: 1.5878 - accuracy: 0.4469 736/3595 [=====>........................] - ETA: 1s - loss: 1.5868 - accuracy: 0.4402 864/3595 [======>.......................] - ETA: 1s - loss: 1.5513 - accuracy: 0.4514 992/3595 [=======>......................] - ETA: 1s - loss: 1.5792 - accuracy: 0.4526 1120/3595 [========>.....................] - ETA: 1s - loss: 1.5981 - accuracy: 0.4464 1216/3595 [=========>....................] - ETA: 1s - loss: 1.5948 - accuracy: 0.4465 1344/3595 [==========>...................] - ETA: 1s - loss: 1.5902 - accuracy: 0.4457 1472/3595 [===========>..................] - ETA: 1s - loss: 1.5915 - accuracy: 0.4436 1600/3595 [============>.................] - ETA: 1s - loss: 1.5852 - accuracy: 0.4444 1696/3595 [=============>................] - ETA: 0s - loss: 1.5817 - accuracy: 0.4440 1824/3595 [==============>...............] - ETA: 0s - loss: 1.5872 - accuracy: 0.4424 1952/3595 [===============>..............] - ETA: 0s - loss: 1.5804 - accuracy: 0.4436 2080/3595 [================>.............] - ETA: 0s - loss: 1.5768 - accuracy: 0.4428 2208/3595 [=================>............] - ETA: 0s - loss: 1.5820 - accuracy: 0.4443 2336/3595 [==================>...........] - ETA: 0s - loss: 1.5828 - accuracy: 0.4473 2464/3595 [===================>..........] - ETA: 0s - loss: 1.5725 - accuracy: 0.4489 2592/3595 [====================>.........] - ETA: 0s - loss: 1.5763 - accuracy: 0.4448 2720/3595 [=====================>........] - ETA: 0s - loss: 1.5835 - accuracy: 0.4401 2848/3595 [======================>.......] - ETA: 0s - loss: 1.5778 - accuracy: 0.4403 2976/3595 [=======================>......] - ETA: 0s - loss: 1.5781 - accuracy: 0.4412 3104/3595 [========================>.....] - ETA: 0s - loss: 1.5700 - accuracy: 0.4420 3200/3595 [=========================>....] - ETA: 0s - loss: 1.5698 - accuracy: 0.4412 3328/3595 [==========================>...] - ETA: 0s - loss: 1.5658 - accuracy: 0.4432 3424/3595 [===========================>..] - ETA: 0s - loss: 1.5612 - accuracy: 0.4436 3552/3595 [============================>.] - ETA: 0s - loss: 1.5626 - accuracy: 0.4426 3595/3595 [==============================] - 2s 566us/sample - loss: 1.5666 - accuracy: 0.4409 - val_loss: 1.4380 - val_accuracy: 0.4828 Epoch 5/28 32/3595 [..............................] - ETA: 1s - loss: 1.1708 - accuracy: 0.5625 128/3595 [>.............................] - ETA: 2s - loss: 1.4585 - accuracy: 0.4531 256/3595 [=>............................] - ETA: 2s - loss: 1.4646 - accuracy: 0.4492 384/3595 [==>...........................] - ETA: 1s - loss: 1.4189 - accuracy: 0.4688 512/3595 [===>..........................] - ETA: 1s - loss: 1.4567 - accuracy: 0.4707 640/3595 [====>.........................] - ETA: 1s - loss: 1.4832 - accuracy: 0.4594 768/3595 [=====>........................] - ETA: 1s - loss: 1.4511 - accuracy: 0.4609 896/3595 [======>.......................] - ETA: 1s - loss: 1.4661 - accuracy: 0.4609 1024/3595 [=======>......................] - ETA: 1s - loss: 1.4798 - accuracy: 0.4531 1152/3595 [========>.....................] - ETA: 1s - loss: 1.4942 - accuracy: 0.4549 1280/3595 [=========>....................] - ETA: 1s - loss: 1.5066 - accuracy: 0.4531 1408/3595 [==========>...................] - ETA: 1s - loss: 1.5015 - accuracy: 0.4560 1536/3595 [===========>..................] - ETA: 1s - loss: 1.5069 - accuracy: 0.4557 1664/3595 [============>.................] - ETA: 1s - loss: 1.4968 - accuracy: 0.4555 1792/3595 [=============>................] - ETA: 0s - loss: 1.5040 - accuracy: 0.4509 1920/3595 [===============>..............] - ETA: 0s - loss: 1.4983 - accuracy: 0.4505 2048/3595 [================>.............] - ETA: 0s - loss: 1.5037 - accuracy: 0.4517 2176/3595 [=================>............] - ETA: 0s - loss: 1.5043 - accuracy: 0.4522 2272/3595 [=================>............] - ETA: 0s - loss: 1.5045 - accuracy: 0.4542 2400/3595 [===================>..........] - ETA: 0s - loss: 1.5135 - accuracy: 0.4542 2528/3595 [====================>.........] - ETA: 0s - loss: 1.5143 - accuracy: 0.4561 2656/3595 [=====================>........] - ETA: 0s - loss: 1.5075 - accuracy: 0.4563 2784/3595 [======================>.......] - ETA: 0s - loss: 1.5044 - accuracy: 0.4569 2912/3595 [=======================>......] - ETA: 0s - loss: 1.4972 - accuracy: 0.4595 3040/3595 [========================>.....] - ETA: 0s - loss: 1.4943 - accuracy: 0.4589 3168/3595 [=========================>....] - ETA: 0s - loss: 1.4917 - accuracy: 0.4593 3296/3595 [==========================>...] - ETA: 0s - loss: 1.4878 - accuracy: 0.4603 3424/3595 [===========================>..] - ETA: 0s - loss: 1.4918 - accuracy: 0.4609 3552/3595 [============================>.] - ETA: 0s - loss: 1.4888 - accuracy: 0.4631 3595/3595 [==============================] - 2s 548us/sample - loss: 1.4903 - accuracy: 0.4634 - val_loss: 1.3819 - val_accuracy: 0.4994 Epoch 6/28 32/3595 [..............................] - ETA: 1s - loss: 1.2284 - accuracy: 0.4375 160/3595 [>.............................] - ETA: 1s - loss: 1.3389 - accuracy: 0.4500 256/3595 [=>............................] - ETA: 1s - loss: 1.3242 - accuracy: 0.4883 384/3595 [==>...........................] - ETA: 1s - loss: 1.3580 - accuracy: 0.4922 512/3595 [===>..........................] - ETA: 1s - loss: 1.3417 - accuracy: 0.5059 640/3595 [====>.........................] - ETA: 1s - loss: 1.3379 - accuracy: 0.5031 736/3595 [=====>........................] - ETA: 1s - loss: 1.3506 - accuracy: 0.4986 864/3595 [======>.......................] - ETA: 1s - loss: 1.3360 - accuracy: 0.5058 992/3595 [=======>......................] - ETA: 1s - loss: 1.3458 - accuracy: 0.5111 1120/3595 [========>.....................] - ETA: 1s - loss: 1.3588 - accuracy: 0.5063 1248/3595 [=========>....................] - ETA: 1s - loss: 1.3791 - accuracy: 0.5008 1376/3595 [==========>...................] - ETA: 1s - loss: 1.3680 - accuracy: 0.5058 1504/3595 [===========>..................] - ETA: 1s - loss: 1.3726 - accuracy: 0.5033 1632/3595 [============>.................] - ETA: 1s - loss: 1.3693 - accuracy: 0.5067 1728/3595 [=============>................] - ETA: 0s - loss: 1.3733 - accuracy: 0.5052 1856/3595 [==============>...............] - ETA: 0s - loss: 1.3868 - accuracy: 0.5022 1984/3595 [===============>..............] - ETA: 0s - loss: 1.3789 - accuracy: 0.5045 2112/3595 [================>.............] - ETA: 0s - loss: 1.3777 - accuracy: 0.5043 2208/3595 [=================>............] - ETA: 0s - loss: 1.3791 - accuracy: 0.5036 2336/3595 [==================>...........] - ETA: 0s - loss: 1.3848 - accuracy: 0.5000 2464/3595 [===================>..........] - ETA: 0s - loss: 1.3819 - accuracy: 0.5008 2592/3595 [====================>.........] - ETA: 0s - loss: 1.3857 - accuracy: 0.4988 2720/3595 [=====================>........] - ETA: 0s - loss: 1.3877 - accuracy: 0.5004 2848/3595 [======================>.......] - ETA: 0s - loss: 1.3895 - accuracy: 0.5011 2976/3595 [=======================>......] - ETA: 0s - loss: 1.3903 - accuracy: 0.5003 3104/3595 [========================>.....] - ETA: 0s - loss: 1.3887 - accuracy: 0.5006 3200/3595 [=========================>....] - ETA: 0s - loss: 1.3861 - accuracy: 0.5016 3328/3595 [==========================>...] - ETA: 0s - loss: 1.3940 - accuracy: 0.4991 3456/3595 [===========================>..] - ETA: 0s - loss: 1.3954 - accuracy: 0.5000 3584/3595 [============================>.] - ETA: 0s - loss: 1.4006 - accuracy: 0.4992 3595/3595 [==============================] - 2s 556us/sample - loss: 1.4004 - accuracy: 0.4990 - val_loss: 1.3325 - val_accuracy: 0.5117 Epoch 7/28 32/3595 [..............................] - ETA: 1s - loss: 1.3185 - accuracy: 0.5312 160/3595 [>.............................] - ETA: 2s - loss: 1.4019 - accuracy: 0.4750 288/3595 [=>............................] - ETA: 1s - loss: 1.3619 - accuracy: 0.4896 416/3595 [==>...........................] - ETA: 1s - loss: 1.3417 - accuracy: 0.5024 544/3595 [===>..........................] - ETA: 1s - loss: 1.3630 - accuracy: 0.4890 672/3595 [====>.........................] - ETA: 1s - loss: 1.3494 - accuracy: 0.4955 800/3595 [=====>........................] - ETA: 1s - loss: 1.3596 - accuracy: 0.4925 928/3595 [======>.......................] - ETA: 1s - loss: 1.3429 - accuracy: 0.5065 1056/3595 [=======>......................] - ETA: 1s - loss: 1.3538 - accuracy: 0.5028 1184/3595 [========>.....................] - ETA: 1s - loss: 1.3466 - accuracy: 0.5042 1312/3595 [=========>....................] - ETA: 1s - loss: 1.3318 - accuracy: 0.5122 1440/3595 [===========>..................] - ETA: 1s - loss: 1.3314 - accuracy: 0.5111 1568/3595 [============>.................] - ETA: 1s - loss: 1.3281 - accuracy: 0.5166 1696/3595 [=============>................] - ETA: 0s - loss: 1.3212 - accuracy: 0.5230 1792/3595 [=============>................] - ETA: 0s - loss: 1.3182 - accuracy: 0.5234 1920/3595 [===============>..............] - ETA: 0s - loss: 1.3199 - accuracy: 0.5260 2016/3595 [===============>..............] - ETA: 0s - loss: 1.3311 - accuracy: 0.5223 2144/3595 [================>.............] - ETA: 0s - loss: 1.3284 - accuracy: 0.5247 2240/3595 [=================>............] - ETA: 0s - loss: 1.3353 - accuracy: 0.5223 2368/3595 [==================>...........] - ETA: 0s - loss: 1.3348 - accuracy: 0.5207 2464/3595 [===================>..........] - ETA: 0s - loss: 1.3379 - accuracy: 0.5227 2560/3595 [====================>.........] - ETA: 0s - loss: 1.3344 - accuracy: 0.5227 2688/3595 [=====================>........] - ETA: 0s - loss: 1.3297 - accuracy: 0.5246 2784/3595 [======================>.......] - ETA: 0s - loss: 1.3299 - accuracy: 0.5241 2880/3595 [=======================>......] - ETA: 0s - loss: 1.3335 - accuracy: 0.5219 2976/3595 [=======================>......] - ETA: 0s - loss: 1.3378 - accuracy: 0.5202 3104/3595 [========================>.....] - ETA: 0s - loss: 1.3365 - accuracy: 0.5216 3200/3595 [=========================>....] - ETA: 0s - loss: 1.3337 - accuracy: 0.5228 3328/3595 [==========================>...] - ETA: 0s - loss: 1.3298 - accuracy: 0.5243 3456/3595 [===========================>..] - ETA: 0s - loss: 1.3301 - accuracy: 0.5255 3584/3595 [============================>.] - ETA: 0s - loss: 1.3297 - accuracy: 0.5243 3595/3595 [==============================] - 2s 577us/sample - loss: 1.3300 - accuracy: 0.5243 - val_loss: 1.2773 - val_accuracy: 0.5350 Epoch 8/28 32/3595 [..............................] - ETA: 1s - loss: 1.0545 - accuracy: 0.5938 160/3595 [>.............................] - ETA: 2s - loss: 1.1840 - accuracy: 0.6000 288/3595 [=>............................] - ETA: 1s - loss: 1.1827 - accuracy: 0.5903 416/3595 [==>...........................] - ETA: 1s - loss: 1.1925 - accuracy: 0.5889 544/3595 [===>..........................] - ETA: 1s - loss: 1.2078 - accuracy: 0.5772 640/3595 [====>.........................] - ETA: 1s - loss: 1.2406 - accuracy: 0.5609 768/3595 [=====>........................] - ETA: 1s - loss: 1.2378 - accuracy: 0.5651 896/3595 [======>.......................] - ETA: 1s - loss: 1.2339 - accuracy: 0.5625 992/3595 [=======>......................] - ETA: 1s - loss: 1.2513 - accuracy: 0.5504 1120/3595 [========>.....................] - ETA: 1s - loss: 1.2651 - accuracy: 0.5464 1216/3595 [=========>....................] - ETA: 1s - loss: 1.2753 - accuracy: 0.5419 1344/3595 [==========>...................] - ETA: 1s - loss: 1.2663 - accuracy: 0.5484 1472/3595 [===========>..................] - ETA: 1s - loss: 1.2799 - accuracy: 0.5442 1568/3595 [============>.................] - ETA: 1s - loss: 1.2735 - accuracy: 0.5466 1696/3595 [=============>................] - ETA: 1s - loss: 1.2687 - accuracy: 0.5478 1824/3595 [==============>...............] - ETA: 0s - loss: 1.2688 - accuracy: 0.5477 1952/3595 [===============>..............] - ETA: 0s - loss: 1.2629 - accuracy: 0.5482 2080/3595 [================>.............] - ETA: 0s - loss: 1.2621 - accuracy: 0.5481 2208/3595 [=================>............] - ETA: 0s - loss: 1.2532 - accuracy: 0.5521 2336/3595 [==================>...........] - ETA: 0s - loss: 1.2554 - accuracy: 0.5522 2464/3595 [===================>..........] - ETA: 0s - loss: 1.2511 - accuracy: 0.5540 2592/3595 [====================>.........] - ETA: 0s - loss: 1.2590 - accuracy: 0.5521 2720/3595 [=====================>........] - ETA: 0s - loss: 1.2565 - accuracy: 0.5533 2848/3595 [======================>.......] - ETA: 0s - loss: 1.2569 - accuracy: 0.5527 2976/3595 [=======================>......] - ETA: 0s - loss: 1.2692 - accuracy: 0.5494 3072/3595 [========================>.....] - ETA: 0s - loss: 1.2710 - accuracy: 0.5479 3200/3595 [=========================>....] - ETA: 0s - loss: 1.2735 - accuracy: 0.5481 3328/3595 [==========================>...] - ETA: 0s - loss: 1.2728 - accuracy: 0.5490 3456/3595 [===========================>..] - ETA: 0s - loss: 1.2713 - accuracy: 0.5489 3584/3595 [============================>.] - ETA: 0s - loss: 1.2701 - accuracy: 0.5485 3595/3595 [==============================] - 2s 555us/sample - loss: 1.2703 - accuracy: 0.5480 - val_loss: 1.2396 - val_accuracy: 0.5584 Epoch 9/28 32/3595 [..............................] - ETA: 1s - loss: 1.2906 - accuracy: 0.5000 160/3595 [>.............................] - ETA: 1s - loss: 1.3163 - accuracy: 0.5312 288/3595 [=>............................] - ETA: 1s - loss: 1.2464 - accuracy: 0.5486 384/3595 [==>...........................] - ETA: 1s - loss: 1.2563 - accuracy: 0.5495 512/3595 [===>..........................] - ETA: 1s - loss: 1.2650 - accuracy: 0.5547 640/3595 [====>.........................] - ETA: 1s - loss: 1.3077 - accuracy: 0.5250 736/3595 [=====>........................] - ETA: 1s - loss: 1.3033 - accuracy: 0.5326 864/3595 [======>.......................] - ETA: 1s - loss: 1.2889 - accuracy: 0.5382 992/3595 [=======>......................] - ETA: 1s - loss: 1.2906 - accuracy: 0.5353 1120/3595 [========>.....................] - ETA: 1s - loss: 1.2990 - accuracy: 0.5295 1248/3595 [=========>....................] - ETA: 1s - loss: 1.3090 - accuracy: 0.5248 1376/3595 [==========>...................] - ETA: 1s - loss: 1.2966 - accuracy: 0.5298 1504/3595 [===========>..................] - ETA: 1s - loss: 1.2872 - accuracy: 0.5346 1632/3595 [============>.................] - ETA: 1s - loss: 1.2832 - accuracy: 0.5337 1760/3595 [=============>................] - ETA: 0s - loss: 1.2763 - accuracy: 0.5386 1888/3595 [==============>...............] - ETA: 0s - loss: 1.2669 - accuracy: 0.5365 2016/3595 [===============>..............] - ETA: 0s - loss: 1.2613 - accuracy: 0.5412 2144/3595 [================>.............] - ETA: 0s - loss: 1.2630 - accuracy: 0.5387 2240/3595 [=================>............] - ETA: 0s - loss: 1.2619 - accuracy: 0.5397 2368/3595 [==================>...........] - ETA: 0s - loss: 1.2543 - accuracy: 0.5405 2496/3595 [===================>..........] - ETA: 0s - loss: 1.2537 - accuracy: 0.5425 2592/3595 [====================>.........] - ETA: 0s - loss: 1.2479 - accuracy: 0.5440 2720/3595 [=====================>........] - ETA: 0s - loss: 1.2483 - accuracy: 0.5441 2848/3595 [======================>.......] - ETA: 0s - loss: 1.2470 - accuracy: 0.5453 2976/3595 [=======================>......] - ETA: 0s - loss: 1.2476 - accuracy: 0.5450 3072/3595 [========================>.....] - ETA: 0s - loss: 1.2482 - accuracy: 0.5456 3200/3595 [=========================>....] - ETA: 0s - loss: 1.2402 - accuracy: 0.5491 3328/3595 [==========================>...] - ETA: 0s - loss: 1.2383 - accuracy: 0.5496 3456/3595 [===========================>..] - ETA: 0s - loss: 1.2344 - accuracy: 0.5515 3552/3595 [============================>.] - ETA: 0s - loss: 1.2318 - accuracy: 0.5526 3595/3595 [==============================] - 2s 557us/sample - loss: 1.2313 - accuracy: 0.5527 - val_loss: 1.2322 - val_accuracy: 0.5573 Epoch 10/28 32/3595 [..............................] - ETA: 1s - loss: 1.0259 - accuracy: 0.5938 160/3595 [>.............................] - ETA: 1s - loss: 1.1395 - accuracy: 0.6062 256/3595 [=>............................] - ETA: 1s - loss: 1.1836 - accuracy: 0.5938 384/3595 [==>...........................] - ETA: 1s - loss: 1.1784 - accuracy: 0.5859 480/3595 [===>..........................] - ETA: 1s - loss: 1.1726 - accuracy: 0.5979 608/3595 [====>.........................] - ETA: 1s - loss: 1.1834 - accuracy: 0.5921 704/3595 [====>.........................] - ETA: 1s - loss: 1.1778 - accuracy: 0.5852 832/3595 [=====>........................] - ETA: 1s - loss: 1.1792 - accuracy: 0.5853 928/3595 [======>.......................] - ETA: 1s - loss: 1.1811 - accuracy: 0.5873 1056/3595 [=======>......................] - ETA: 1s - loss: 1.1874 - accuracy: 0.5843 1184/3595 [========>.....................] - ETA: 1s - loss: 1.1808 - accuracy: 0.5819 1280/3595 [=========>....................] - ETA: 1s - loss: 1.1715 - accuracy: 0.5828 1376/3595 [==========>...................] - ETA: 1s - loss: 1.1668 - accuracy: 0.5858 1504/3595 [===========>..................] - ETA: 1s - loss: 1.1858 - accuracy: 0.5811 1632/3595 [============>.................] - ETA: 1s - loss: 1.1842 - accuracy: 0.5797 1760/3595 [=============>................] - ETA: 1s - loss: 1.1889 - accuracy: 0.5767 1888/3595 [==============>...............] - ETA: 0s - loss: 1.1801 - accuracy: 0.5763 2016/3595 [===============>..............] - ETA: 0s - loss: 1.1822 - accuracy: 0.5744 2144/3595 [================>.............] - ETA: 0s - loss: 1.1756 - accuracy: 0.5756 2272/3595 [=================>............] - ETA: 0s - loss: 1.1789 - accuracy: 0.5731 2400/3595 [===================>..........] - ETA: 0s - loss: 1.1817 - accuracy: 0.5729 2528/3595 [====================>.........] - ETA: 0s - loss: 1.1833 - accuracy: 0.5720 2656/3595 [=====================>........] - ETA: 0s - loss: 1.1856 - accuracy: 0.5734 2784/3595 [======================>.......] - ETA: 0s - loss: 1.1863 - accuracy: 0.5736 2880/3595 [=======================>......] - ETA: 0s - loss: 1.1796 - accuracy: 0.5760 3008/3595 [========================>.....] - ETA: 0s - loss: 1.1787 - accuracy: 0.5761 3136/3595 [=========================>....] - ETA: 0s - loss: 1.1772 - accuracy: 0.5762 3264/3595 [==========================>...] - ETA: 0s - loss: 1.1781 - accuracy: 0.5754 3392/3595 [===========================>..] - ETA: 0s - loss: 1.1779 - accuracy: 0.5775 3520/3595 [============================>.] - ETA: 0s - loss: 1.1812 - accuracy: 0.5759 3595/3595 [==============================] - 2s 566us/sample - loss: 1.1788 - accuracy: 0.5750 - val_loss: 1.1899 - val_accuracy: 0.5729 Epoch 11/28 32/3595 [..............................] - ETA: 1s - loss: 1.4495 - accuracy: 0.4688 160/3595 [>.............................] - ETA: 2s - loss: 1.1373 - accuracy: 0.5750 288/3595 [=>............................] - ETA: 1s - loss: 1.0885 - accuracy: 0.5833 416/3595 [==>...........................] - ETA: 1s - loss: 1.1517 - accuracy: 0.5673 512/3595 [===>..........................] - ETA: 1s - loss: 1.1645 - accuracy: 0.5684 640/3595 [====>.........................] - ETA: 1s - loss: 1.1777 - accuracy: 0.5688 768/3595 [=====>........................] - ETA: 1s - loss: 1.1787 - accuracy: 0.5703 896/3595 [======>.......................] - ETA: 1s - loss: 1.1866 - accuracy: 0.5703 1024/3595 [=======>......................] - ETA: 1s - loss: 1.1735 - accuracy: 0.5732 1152/3595 [========>.....................] - ETA: 1s - loss: 1.1764 - accuracy: 0.5720 1280/3595 [=========>....................] - ETA: 1s - loss: 1.1717 - accuracy: 0.5742 1408/3595 [==========>...................] - ETA: 1s - loss: 1.1689 - accuracy: 0.5753 1536/3595 [===========>..................] - ETA: 1s - loss: 1.1640 - accuracy: 0.5788 1632/3595 [============>.................] - ETA: 1s - loss: 1.1667 - accuracy: 0.5754 1760/3595 [=============>................] - ETA: 0s - loss: 1.1640 - accuracy: 0.5744 1888/3595 [==============>...............] - ETA: 0s - loss: 1.1564 - accuracy: 0.5805 2016/3595 [===============>..............] - ETA: 0s - loss: 1.1546 - accuracy: 0.5799 2144/3595 [================>.............] - ETA: 0s - loss: 1.1538 - accuracy: 0.5807 2240/3595 [=================>............] - ETA: 0s - loss: 1.1596 - accuracy: 0.5768 2368/3595 [==================>...........] - ETA: 0s - loss: 1.1679 - accuracy: 0.5756 2496/3595 [===================>..........] - ETA: 0s - loss: 1.1612 - accuracy: 0.5781 2624/3595 [====================>.........] - ETA: 0s - loss: 1.1559 - accuracy: 0.5808 2752/3595 [=====================>........] - ETA: 0s - loss: 1.1554 - accuracy: 0.5818 2880/3595 [=======================>......] - ETA: 0s - loss: 1.1462 - accuracy: 0.5865 3008/3595 [========================>.....] - ETA: 0s - loss: 1.1480 - accuracy: 0.5861 3104/3595 [========================>.....] - ETA: 0s - loss: 1.1467 - accuracy: 0.5880 3232/3595 [=========================>....] - ETA: 0s - loss: 1.1522 - accuracy: 0.5848 3360/3595 [===========================>..] - ETA: 0s - loss: 1.1535 - accuracy: 0.5851 3488/3595 [============================>.] - ETA: 0s - loss: 1.1516 - accuracy: 0.5866 3595/3595 [==============================] - 2s 549us/sample - loss: 1.1474 - accuracy: 0.5880 - val_loss: 1.1643 - val_accuracy: 0.5862 Epoch 12/28 32/3595 [..............................] - ETA: 1s - loss: 1.1148 - accuracy: 0.6250 128/3595 [>.............................] - ETA: 2s - loss: 1.0651 - accuracy: 0.6484 256/3595 [=>............................] - ETA: 1s - loss: 1.0870 - accuracy: 0.6250 384/3595 [==>...........................] - ETA: 1s - loss: 1.1113 - accuracy: 0.6172 512/3595 [===>..........................] - ETA: 1s - loss: 1.0880 - accuracy: 0.6309 608/3595 [====>.........................] - ETA: 1s - loss: 1.0833 - accuracy: 0.6283 736/3595 [=====>........................] - ETA: 1s - loss: 1.1058 - accuracy: 0.6073 864/3595 [======>.......................] - ETA: 1s - loss: 1.0977 - accuracy: 0.6030 992/3595 [=======>......................] - ETA: 1s - loss: 1.0979 - accuracy: 0.6038 1120/3595 [========>.....................] - ETA: 1s - loss: 1.1012 - accuracy: 0.6000 1248/3595 [=========>....................] - ETA: 1s - loss: 1.0989 - accuracy: 0.5986 1376/3595 [==========>...................] - ETA: 1s - loss: 1.0897 - accuracy: 0.6039 1504/3595 [===========>..................] - ETA: 1s - loss: 1.0894 - accuracy: 0.6024 1632/3595 [============>.................] - ETA: 1s - loss: 1.0848 - accuracy: 0.6060 1760/3595 [=============>................] - ETA: 0s - loss: 1.0863 - accuracy: 0.6028 1888/3595 [==============>...............] - ETA: 0s - loss: 1.0891 - accuracy: 0.6006 2016/3595 [===============>..............] - ETA: 0s - loss: 1.0861 - accuracy: 0.6022 2112/3595 [================>.............] - ETA: 0s - loss: 1.0899 - accuracy: 0.5999 2240/3595 [=================>............] - ETA: 0s - loss: 1.0945 - accuracy: 0.5978 2368/3595 [==================>...........] - ETA: 0s - loss: 1.0982 - accuracy: 0.5971 2496/3595 [===================>..........] - ETA: 0s - loss: 1.0958 - accuracy: 0.6002 2624/3595 [====================>.........] - ETA: 0s - loss: 1.0976 - accuracy: 0.6006 2752/3595 [=====================>........] - ETA: 0s - loss: 1.0974 - accuracy: 0.5996 2880/3595 [=======================>......] - ETA: 0s - loss: 1.1060 - accuracy: 0.5972 3008/3595 [========================>.....] - ETA: 0s - loss: 1.1070 - accuracy: 0.5957 3104/3595 [========================>.....] - ETA: 0s - loss: 1.0989 - accuracy: 0.5989 3232/3595 [=========================>....] - ETA: 0s - loss: 1.0947 - accuracy: 0.6002 3328/3595 [==========================>...] - ETA: 0s - loss: 1.0968 - accuracy: 0.5992 3456/3595 [===========================>..] - ETA: 0s - loss: 1.0983 - accuracy: 0.5987 3552/3595 [============================>.] - ETA: 0s - loss: 1.0999 - accuracy: 0.5954 3595/3595 [==============================] - 2s 557us/sample - loss: 1.0996 - accuracy: 0.5961 - val_loss: 1.1525 - val_accuracy: 0.5907 Epoch 13/28 32/3595 [..............................] - ETA: 1s - loss: 1.0281 - accuracy: 0.5938 128/3595 [>.............................] - ETA: 2s - loss: 0.9237 - accuracy: 0.6875 256/3595 [=>............................] - ETA: 2s - loss: 1.0379 - accuracy: 0.6523 352/3595 [=>............................] - ETA: 2s - loss: 1.0929 - accuracy: 0.6193 480/3595 [===>..........................] - ETA: 1s - loss: 1.0599 - accuracy: 0.6104 608/3595 [====>.........................] - ETA: 1s - loss: 1.0506 - accuracy: 0.6184 736/3595 [=====>........................] - ETA: 1s - loss: 1.0685 - accuracy: 0.6141 864/3595 [======>.......................] - ETA: 1s - loss: 1.0718 - accuracy: 0.6134 960/3595 [=======>......................] - ETA: 1s - loss: 1.0969 - accuracy: 0.6031 1088/3595 [========>.....................] - ETA: 1s - loss: 1.1054 - accuracy: 0.6039 1216/3595 [=========>....................] - ETA: 1s - loss: 1.1161 - accuracy: 0.5962 1344/3595 [==========>...................] - ETA: 1s - loss: 1.1069 - accuracy: 0.5997 1472/3595 [===========>..................] - ETA: 1s - loss: 1.1024 - accuracy: 0.6012 1600/3595 [============>.................] - ETA: 1s - loss: 1.0993 - accuracy: 0.6019 1728/3595 [=============>................] - ETA: 0s - loss: 1.0990 - accuracy: 0.6024 1824/3595 [==============>...............] - ETA: 0s - loss: 1.1027 - accuracy: 0.5987 1952/3595 [===============>..............] - ETA: 0s - loss: 1.1047 - accuracy: 0.5978 2080/3595 [================>.............] - ETA: 0s - loss: 1.1001 - accuracy: 0.6010 2208/3595 [=================>............] - ETA: 0s - loss: 1.0937 - accuracy: 0.6051 2336/3595 [==================>...........] - ETA: 0s - loss: 1.0914 - accuracy: 0.6074 2464/3595 [===================>..........] - ETA: 0s - loss: 1.0834 - accuracy: 0.6120 2592/3595 [====================>.........] - ETA: 0s - loss: 1.0753 - accuracy: 0.6142 2720/3595 [=====================>........] - ETA: 0s - loss: 1.0734 - accuracy: 0.6154 2848/3595 [======================>.......] - ETA: 0s - loss: 1.0698 - accuracy: 0.6173 2976/3595 [=======================>......] - ETA: 0s - loss: 1.0666 - accuracy: 0.6169 3104/3595 [========================>.....] - ETA: 0s - loss: 1.0567 - accuracy: 0.6215 3200/3595 [=========================>....] - ETA: 0s - loss: 1.0530 - accuracy: 0.6216 3328/3595 [==========================>...] - ETA: 0s - loss: 1.0521 - accuracy: 0.6217 3456/3595 [===========================>..] - ETA: 0s - loss: 1.0488 - accuracy: 0.6224 3584/3595 [============================>.] - ETA: 0s - loss: 1.0534 - accuracy: 0.6228 3595/3595 [==============================] - 2s 548us/sample - loss: 1.0532 - accuracy: 0.6234 - val_loss: 1.1291 - val_accuracy: 0.6096 Epoch 14/28 32/3595 [..............................] - ETA: 1s - loss: 0.9791 - accuracy: 0.6875 128/3595 [>.............................] - ETA: 2s - loss: 0.9683 - accuracy: 0.6562 256/3595 [=>............................] - ETA: 1s - loss: 0.9931 - accuracy: 0.6289 384/3595 [==>...........................] - ETA: 1s - loss: 1.0505 - accuracy: 0.6172 480/3595 [===>..........................] - ETA: 1s - loss: 1.0505 - accuracy: 0.6104 608/3595 [====>.........................] - ETA: 1s - loss: 1.0567 - accuracy: 0.6118 736/3595 [=====>........................] - ETA: 1s - loss: 1.0678 - accuracy: 0.6019 832/3595 [=====>........................] - ETA: 1s - loss: 1.0570 - accuracy: 0.6154 960/3595 [=======>......................] - ETA: 1s - loss: 1.0674 - accuracy: 0.6115 1088/3595 [========>.....................] - ETA: 1s - loss: 1.0438 - accuracy: 0.6195 1184/3595 [========>.....................] - ETA: 1s - loss: 1.0519 - accuracy: 0.6216 1312/3595 [=========>....................] - ETA: 1s - loss: 1.0660 - accuracy: 0.6204 1440/3595 [===========>..................] - ETA: 1s - loss: 1.0598 - accuracy: 0.6222 1568/3595 [============>.................] - ETA: 1s - loss: 1.0593 - accuracy: 0.6237 1664/3595 [============>.................] - ETA: 1s - loss: 1.0478 - accuracy: 0.6262 1792/3595 [=============>................] - ETA: 0s - loss: 1.0455 - accuracy: 0.6256 1920/3595 [===============>..............] - ETA: 0s - loss: 1.0537 - accuracy: 0.6255 2048/3595 [================>.............] - ETA: 0s - loss: 1.0451 - accuracy: 0.6294 2144/3595 [================>.............] - ETA: 0s - loss: 1.0421 - accuracy: 0.6325 2272/3595 [=================>............] - ETA: 0s - loss: 1.0375 - accuracy: 0.6360 2400/3595 [===================>..........] - ETA: 0s - loss: 1.0246 - accuracy: 0.6404 2496/3595 [===================>..........] - ETA: 0s - loss: 1.0215 - accuracy: 0.6386 2624/3595 [====================>.........] - ETA: 0s - loss: 1.0227 - accuracy: 0.6357 2752/3595 [=====================>........] - ETA: 0s - loss: 1.0237 - accuracy: 0.6374 2880/3595 [=======================>......] - ETA: 0s - loss: 1.0250 - accuracy: 0.6351 3008/3595 [========================>.....] - ETA: 0s - loss: 1.0167 - accuracy: 0.6383 3104/3595 [========================>.....] - ETA: 0s - loss: 1.0189 - accuracy: 0.6385 3232/3595 [=========================>....] - ETA: 0s - loss: 1.0183 - accuracy: 0.6374 3360/3595 [===========================>..] - ETA: 0s - loss: 1.0214 - accuracy: 0.6369 3488/3595 [============================>.] - ETA: 0s - loss: 1.0254 - accuracy: 0.6368 3584/3595 [============================>.] - ETA: 0s - loss: 1.0259 - accuracy: 0.6367 3595/3595 [==============================] - 2s 561us/sample - loss: 1.0273 - accuracy: 0.6359 - val_loss: 1.1049 - val_accuracy: 0.6040 Epoch 15/28 32/3595 [..............................] - ETA: 1s - loss: 0.9217 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 1s - loss: 0.9710 - accuracy: 0.6500 256/3595 [=>............................] - ETA: 1s - loss: 0.9965 - accuracy: 0.6406 384/3595 [==>...........................] - ETA: 1s - loss: 1.0103 - accuracy: 0.6406 512/3595 [===>..........................] - ETA: 1s - loss: 1.0116 - accuracy: 0.6465 608/3595 [====>.........................] - ETA: 1s - loss: 0.9953 - accuracy: 0.6497 736/3595 [=====>........................] - ETA: 1s - loss: 0.9829 - accuracy: 0.6522 864/3595 [======>.......................] - ETA: 1s - loss: 0.9847 - accuracy: 0.6597 992/3595 [=======>......................] - ETA: 1s - loss: 0.9862 - accuracy: 0.6623 1120/3595 [========>.....................] - ETA: 1s - loss: 1.0030 - accuracy: 0.6518 1216/3595 [=========>....................] - ETA: 1s - loss: 0.9924 - accuracy: 0.6587 1344/3595 [==========>...................] - ETA: 1s - loss: 0.9876 - accuracy: 0.6622 1472/3595 [===========>..................] - ETA: 1s - loss: 0.9918 - accuracy: 0.6562 1600/3595 [============>.................] - ETA: 1s - loss: 0.9818 - accuracy: 0.6600 1728/3595 [=============>................] - ETA: 0s - loss: 0.9835 - accuracy: 0.6591 1856/3595 [==============>...............] - ETA: 0s - loss: 0.9869 - accuracy: 0.6568 1984/3595 [===============>..............] - ETA: 0s - loss: 0.9915 - accuracy: 0.6557 2112/3595 [================>.............] - ETA: 0s - loss: 0.9896 - accuracy: 0.6577 2240/3595 [=================>............] - ETA: 0s - loss: 0.9838 - accuracy: 0.6589 2336/3595 [==================>...........] - ETA: 0s - loss: 0.9867 - accuracy: 0.6571 2464/3595 [===================>..........] - ETA: 0s - loss: 0.9910 - accuracy: 0.6571 2592/3595 [====================>.........] - ETA: 0s - loss: 0.9923 - accuracy: 0.6543 2720/3595 [=====================>........] - ETA: 0s - loss: 0.9936 - accuracy: 0.6540 2816/3595 [======================>.......] - ETA: 0s - loss: 0.9910 - accuracy: 0.6559 2944/3595 [=======================>......] - ETA: 0s - loss: 0.9879 - accuracy: 0.6559 3072/3595 [========================>.....] - ETA: 0s - loss: 0.9866 - accuracy: 0.6569 3168/3595 [=========================>....] - ETA: 0s - loss: 0.9927 - accuracy: 0.6544 3296/3595 [==========================>...] - ETA: 0s - loss: 0.9992 - accuracy: 0.6505 3424/3595 [===========================>..] - ETA: 0s - loss: 1.0017 - accuracy: 0.6495 3552/3595 [============================>.] - ETA: 0s - loss: 1.0063 - accuracy: 0.6472 3595/3595 [==============================] - 2s 572us/sample - loss: 1.0031 - accuracy: 0.6487 - val_loss: 1.0930 - val_accuracy: 0.6140 Epoch 16/28 32/3595 [..............................] - ETA: 3s - loss: 0.7090 - accuracy: 0.7500 160/3595 [>.............................] - ETA: 2s - loss: 0.8731 - accuracy: 0.6875 288/3595 [=>............................] - ETA: 1s - loss: 0.9134 - accuracy: 0.6736 384/3595 [==>...........................] - ETA: 1s - loss: 0.8898 - accuracy: 0.6823 512/3595 [===>..........................] - ETA: 1s - loss: 0.8971 - accuracy: 0.6816 640/3595 [====>.........................] - ETA: 1s - loss: 0.8763 - accuracy: 0.6984 768/3595 [=====>........................] - ETA: 1s - loss: 0.8713 - accuracy: 0.6966 864/3595 [======>.......................] - ETA: 1s - loss: 0.9101 - accuracy: 0.6829 992/3595 [=======>......................] - ETA: 1s - loss: 0.9190 - accuracy: 0.6794 1088/3595 [========>.....................] - ETA: 1s - loss: 0.9261 - accuracy: 0.6774 1216/3595 [=========>....................] - ETA: 1s - loss: 0.9253 - accuracy: 0.6735 1344/3595 [==========>...................] - ETA: 1s - loss: 0.9345 - accuracy: 0.6719 1472/3595 [===========>..................] - ETA: 1s - loss: 0.9322 - accuracy: 0.6712 1600/3595 [============>.................] - ETA: 1s - loss: 0.9340 - accuracy: 0.6687 1728/3595 [=============>................] - ETA: 0s - loss: 0.9364 - accuracy: 0.6661 1856/3595 [==============>...............] - ETA: 0s - loss: 0.9310 - accuracy: 0.6697 1952/3595 [===============>..............] - ETA: 0s - loss: 0.9318 - accuracy: 0.6696 2080/3595 [================>.............] - ETA: 0s - loss: 0.9366 - accuracy: 0.6673 2208/3595 [=================>............] - ETA: 0s - loss: 0.9453 - accuracy: 0.6644 2336/3595 [==================>...........] - ETA: 0s - loss: 0.9514 - accuracy: 0.6618 2432/3595 [===================>..........] - ETA: 0s - loss: 0.9449 - accuracy: 0.6653 2560/3595 [====================>.........] - ETA: 0s - loss: 0.9427 - accuracy: 0.6652 2688/3595 [=====================>........] - ETA: 0s - loss: 0.9428 - accuracy: 0.6663 2816/3595 [======================>.......] - ETA: 0s - loss: 0.9500 - accuracy: 0.6623 2944/3595 [=======================>......] - ETA: 0s - loss: 0.9472 - accuracy: 0.6627 3040/3595 [========================>.....] - ETA: 0s - loss: 0.9502 - accuracy: 0.6602 3168/3595 [=========================>....] - ETA: 0s - loss: 0.9593 - accuracy: 0.6566 3296/3595 [==========================>...] - ETA: 0s - loss: 0.9609 - accuracy: 0.6566 3424/3595 [===========================>..] - ETA: 0s - loss: 0.9590 - accuracy: 0.6583 3552/3595 [============================>.] - ETA: 0s - loss: 0.9582 - accuracy: 0.6568 3595/3595 [==============================] - 2s 555us/sample - loss: 0.9593 - accuracy: 0.6554 - val_loss: 1.0994 - val_accuracy: 0.6107 Epoch 17/28 32/3595 [..............................] - ETA: 1s - loss: 0.8379 - accuracy: 0.7188 160/3595 [>.............................] - ETA: 1s - loss: 0.9206 - accuracy: 0.6750 256/3595 [=>............................] - ETA: 1s - loss: 0.9226 - accuracy: 0.6602 384/3595 [==>...........................] - ETA: 1s - loss: 0.9611 - accuracy: 0.6484 512/3595 [===>..........................] - ETA: 1s - loss: 0.9182 - accuracy: 0.6777 608/3595 [====>.........................] - ETA: 1s - loss: 0.9443 - accuracy: 0.6678 736/3595 [=====>........................] - ETA: 1s - loss: 0.9210 - accuracy: 0.6766 864/3595 [======>.......................] - ETA: 1s - loss: 0.9063 - accuracy: 0.6852 960/3595 [=======>......................] - ETA: 1s - loss: 0.9160 - accuracy: 0.6833 1088/3595 [========>.....................] - ETA: 1s - loss: 0.9304 - accuracy: 0.6792 1216/3595 [=========>....................] - ETA: 1s - loss: 0.9332 - accuracy: 0.6752 1344/3595 [==========>...................] - ETA: 1s - loss: 0.9432 - accuracy: 0.6704 1440/3595 [===========>..................] - ETA: 1s - loss: 0.9333 - accuracy: 0.6736 1568/3595 [============>.................] - ETA: 1s - loss: 0.9273 - accuracy: 0.6747 1696/3595 [=============>................] - ETA: 1s - loss: 0.9216 - accuracy: 0.6798 1824/3595 [==============>...............] - ETA: 0s - loss: 0.9190 - accuracy: 0.6815 1952/3595 [===============>..............] - ETA: 0s - loss: 0.9191 - accuracy: 0.6819 2048/3595 [================>.............] - ETA: 0s - loss: 0.9166 - accuracy: 0.6836 2176/3595 [=================>............] - ETA: 0s - loss: 0.9265 - accuracy: 0.6792 2304/3595 [==================>...........] - ETA: 0s - loss: 0.9285 - accuracy: 0.6775 2432/3595 [===================>..........] - ETA: 0s - loss: 0.9259 - accuracy: 0.6822 2560/3595 [====================>.........] - ETA: 0s - loss: 0.9222 - accuracy: 0.6820 2688/3595 [=====================>........] - ETA: 0s - loss: 0.9180 - accuracy: 0.6823 2816/3595 [======================>.......] - ETA: 0s - loss: 0.9248 - accuracy: 0.6808 2944/3595 [=======================>......] - ETA: 0s - loss: 0.9283 - accuracy: 0.6787 3040/3595 [========================>.....] - ETA: 0s - loss: 0.9279 - accuracy: 0.6766 3168/3595 [=========================>....] - ETA: 0s - loss: 0.9211 - accuracy: 0.6787 3296/3595 [==========================>...] - ETA: 0s - loss: 0.9220 - accuracy: 0.6796 3424/3595 [===========================>..] - ETA: 0s - loss: 0.9249 - accuracy: 0.6782 3552/3595 [============================>.] - ETA: 0s - loss: 0.9211 - accuracy: 0.6793 3595/3595 [==============================] - 2s 553us/sample - loss: 0.9205 - accuracy: 0.6796 - val_loss: 1.0765 - val_accuracy: 0.6218 Epoch 18/28 32/3595 [..............................] - ETA: 3s - loss: 0.9837 - accuracy: 0.6250 160/3595 [>.............................] - ETA: 2s - loss: 0.8250 - accuracy: 0.6938 288/3595 [=>............................] - ETA: 1s - loss: 0.8073 - accuracy: 0.7049 416/3595 [==>...........................] - ETA: 1s - loss: 0.8324 - accuracy: 0.7019 512/3595 [===>..........................] - ETA: 1s - loss: 0.8453 - accuracy: 0.6992 640/3595 [====>.........................] - ETA: 1s - loss: 0.8614 - accuracy: 0.6922 768/3595 [=====>........................] - ETA: 1s - loss: 0.8809 - accuracy: 0.6888 896/3595 [======>.......................] - ETA: 1s - loss: 0.8803 - accuracy: 0.6853 1024/3595 [=======>......................] - ETA: 1s - loss: 0.9074 - accuracy: 0.6758 1120/3595 [========>.....................] - ETA: 1s - loss: 0.9081 - accuracy: 0.6705 1216/3595 [=========>....................] - ETA: 1s - loss: 0.9109 - accuracy: 0.6694 1312/3595 [=========>....................] - ETA: 1s - loss: 0.9276 - accuracy: 0.6616 1408/3595 [==========>...................] - ETA: 1s - loss: 0.9234 - accuracy: 0.6641 1504/3595 [===========>..................] - ETA: 1s - loss: 0.9119 - accuracy: 0.6669 1632/3595 [============>.................] - ETA: 1s - loss: 0.9083 - accuracy: 0.6710 1760/3595 [=============>................] - ETA: 1s - loss: 0.9185 - accuracy: 0.6676 1888/3595 [==============>...............] - ETA: 0s - loss: 0.9092 - accuracy: 0.6737 2016/3595 [===============>..............] - ETA: 0s - loss: 0.9056 - accuracy: 0.6761 2144/3595 [================>.............] - ETA: 0s - loss: 0.9124 - accuracy: 0.6735 2272/3595 [=================>............] - ETA: 0s - loss: 0.9091 - accuracy: 0.6743 2400/3595 [===================>..........] - ETA: 0s - loss: 0.9055 - accuracy: 0.6758 2528/3595 [====================>.........] - ETA: 0s - loss: 0.9078 - accuracy: 0.6748 2656/3595 [=====================>........] - ETA: 0s - loss: 0.9132 - accuracy: 0.6709 2784/3595 [======================>.......] - ETA: 0s - loss: 0.9125 - accuracy: 0.6688 2912/3595 [=======================>......] - ETA: 0s - loss: 0.9134 - accuracy: 0.6672 3008/3595 [========================>.....] - ETA: 0s - loss: 0.9120 - accuracy: 0.6662 3136/3595 [=========================>....] - ETA: 0s - loss: 0.9088 - accuracy: 0.6684 3264/3595 [==========================>...] - ETA: 0s - loss: 0.9045 - accuracy: 0.6716 3392/3595 [===========================>..] - ETA: 0s - loss: 0.8957 - accuracy: 0.6754 3488/3595 [============================>.] - ETA: 0s - loss: 0.8954 - accuracy: 0.6757 3595/3595 [==============================] - 2s 566us/sample - loss: 0.8946 - accuracy: 0.6765 - val_loss: 1.0729 - val_accuracy: 0.6118 Epoch 19/28 32/3595 [..............................] - ETA: 1s - loss: 0.9834 - accuracy: 0.6875 160/3595 [>.............................] - ETA: 1s - loss: 0.8437 - accuracy: 0.6875 288/3595 [=>............................] - ETA: 1s - loss: 0.8366 - accuracy: 0.6944 384/3595 [==>...........................] - ETA: 1s - loss: 0.8409 - accuracy: 0.7005 512/3595 [===>..........................] - ETA: 1s - loss: 0.8333 - accuracy: 0.7109 640/3595 [====>.........................] - ETA: 1s - loss: 0.8280 - accuracy: 0.7172 736/3595 [=====>........................] - ETA: 1s - loss: 0.7991 - accuracy: 0.7283 864/3595 [======>.......................] - ETA: 1s - loss: 0.8135 - accuracy: 0.7199 992/3595 [=======>......................] - ETA: 1s - loss: 0.8324 - accuracy: 0.7097 1088/3595 [========>.....................] - ETA: 1s - loss: 0.8455 - accuracy: 0.7077 1216/3595 [=========>....................] - ETA: 1s - loss: 0.8400 - accuracy: 0.7089 1344/3595 [==========>...................] - ETA: 1s - loss: 0.8443 - accuracy: 0.7009 1472/3595 [===========>..................] - ETA: 1s - loss: 0.8501 - accuracy: 0.6977 1568/3595 [============>.................] - ETA: 1s - loss: 0.8545 - accuracy: 0.6977 1696/3595 [=============>................] - ETA: 0s - loss: 0.8594 - accuracy: 0.6981 1824/3595 [==============>...............] - ETA: 0s - loss: 0.8619 - accuracy: 0.7001 1952/3595 [===============>..............] - ETA: 0s - loss: 0.8658 - accuracy: 0.6967 2048/3595 [================>.............] - ETA: 0s - loss: 0.8714 - accuracy: 0.6948 2176/3595 [=================>............] - ETA: 0s - loss: 0.8702 - accuracy: 0.6935 2304/3595 [==================>...........] - ETA: 0s - loss: 0.8730 - accuracy: 0.6936 2432/3595 [===================>..........] - ETA: 0s - loss: 0.8689 - accuracy: 0.6941 2528/3595 [====================>.........] - ETA: 0s - loss: 0.8713 - accuracy: 0.6942 2656/3595 [=====================>........] - ETA: 0s - loss: 0.8706 - accuracy: 0.6954 2784/3595 [======================>.......] - ETA: 0s - loss: 0.8701 - accuracy: 0.6940 2912/3595 [=======================>......] - ETA: 0s - loss: 0.8805 - accuracy: 0.6892 3008/3595 [========================>.....] - ETA: 0s - loss: 0.8761 - accuracy: 0.6905 3136/3595 [=========================>....] - ETA: 0s - loss: 0.8767 - accuracy: 0.6910 3264/3595 [==========================>...] - ETA: 0s - loss: 0.8709 - accuracy: 0.6930 3392/3595 [===========================>..] - ETA: 0s - loss: 0.8663 - accuracy: 0.6952 3488/3595 [============================>.] - ETA: 0s - loss: 0.8671 - accuracy: 0.6950 3595/3595 [==============================] - 2s 557us/sample - loss: 0.8691 - accuracy: 0.6943 - val_loss: 1.0505 - val_accuracy: 0.6318 Epoch 20/28 32/3595 [..............................] - ETA: 1s - loss: 0.7057 - accuracy: 0.7500 160/3595 [>.............................] - ETA: 2s - loss: 0.7959 - accuracy: 0.7125 288/3595 [=>............................] - ETA: 1s - loss: 0.8059 - accuracy: 0.7083 416/3595 [==>...........................] - ETA: 1s - loss: 0.8174 - accuracy: 0.6923 512/3595 [===>..........................] - ETA: 1s - loss: 0.8244 - accuracy: 0.6973 640/3595 [====>.........................] - ETA: 1s - loss: 0.8075 - accuracy: 0.7078 768/3595 [=====>........................] - ETA: 1s - loss: 0.8285 - accuracy: 0.6979 864/3595 [======>.......................] - ETA: 1s - loss: 0.8332 - accuracy: 0.7002 992/3595 [=======>......................] - ETA: 1s - loss: 0.8388 - accuracy: 0.6976 1088/3595 [========>.....................] - ETA: 1s - loss: 0.8342 - accuracy: 0.7040 1184/3595 [========>.....................] - ETA: 1s - loss: 0.8273 - accuracy: 0.7061 1312/3595 [=========>....................] - ETA: 1s - loss: 0.8165 - accuracy: 0.7081 1440/3595 [===========>..................] - ETA: 1s - loss: 0.8177 - accuracy: 0.7069 1568/3595 [============>.................] - ETA: 1s - loss: 0.8254 - accuracy: 0.7054 1664/3595 [============>.................] - ETA: 1s - loss: 0.8227 - accuracy: 0.7085 1792/3595 [=============>................] - ETA: 0s - loss: 0.8216 - accuracy: 0.7104 1920/3595 [===============>..............] - ETA: 0s - loss: 0.8204 - accuracy: 0.7083 2048/3595 [================>.............] - ETA: 0s - loss: 0.8285 - accuracy: 0.7021 2144/3595 [================>.............] - ETA: 0s - loss: 0.8257 - accuracy: 0.7034 2272/3595 [=================>............] - ETA: 0s - loss: 0.8202 - accuracy: 0.7086 2400/3595 [===================>..........] - ETA: 0s - loss: 0.8266 - accuracy: 0.7071 2528/3595 [====================>.........] - ETA: 0s - loss: 0.8244 - accuracy: 0.7061 2624/3595 [====================>.........] - ETA: 0s - loss: 0.8236 - accuracy: 0.7073 2752/3595 [=====================>........] - ETA: 0s - loss: 0.8201 - accuracy: 0.7108 2848/3595 [======================>.......] - ETA: 0s - loss: 0.8177 - accuracy: 0.7121 2976/3595 [=======================>......] - ETA: 0s - loss: 0.8225 - accuracy: 0.7107 3072/3595 [========================>.....] - ETA: 0s - loss: 0.8263 - accuracy: 0.7083 3200/3595 [=========================>....] - ETA: 0s - loss: 0.8329 - accuracy: 0.7066 3328/3595 [==========================>...] - ETA: 0s - loss: 0.8300 - accuracy: 0.7073 3456/3595 [===========================>..] - ETA: 0s - loss: 0.8266 - accuracy: 0.7092 3552/3595 [============================>.] - ETA: 0s - loss: 0.8300 - accuracy: 0.7083 3595/3595 [==============================] - 2s 570us/sample - loss: 0.8357 - accuracy: 0.7057 - val_loss: 1.0397 - val_accuracy: 0.6207 Epoch 21/28 32/3595 [..............................] - ETA: 3s - loss: 0.9467 - accuracy: 0.8125 160/3595 [>.............................] - ETA: 2s - loss: 0.8853 - accuracy: 0.7125 288/3595 [=>............................] - ETA: 1s - loss: 0.8173 - accuracy: 0.7257 416/3595 [==>...........................] - ETA: 1s - loss: 0.7932 - accuracy: 0.7332 544/3595 [===>..........................] - ETA: 1s - loss: 0.7762 - accuracy: 0.7408 672/3595 [====>.........................] - ETA: 1s - loss: 0.7880 - accuracy: 0.7351 800/3595 [=====>........................] - ETA: 1s - loss: 0.8057 - accuracy: 0.7337 928/3595 [======>.......................] - ETA: 1s - loss: 0.7930 - accuracy: 0.7328 1056/3595 [=======>......................] - ETA: 1s - loss: 0.7912 - accuracy: 0.7301 1184/3595 [========>.....................] - ETA: 1s - loss: 0.7979 - accuracy: 0.7280 1312/3595 [=========>....................] - ETA: 1s - loss: 0.8079 - accuracy: 0.7287 1440/3595 [===========>..................] - ETA: 1s - loss: 0.8118 - accuracy: 0.7285 1568/3595 [============>.................] - ETA: 1s - loss: 0.8085 - accuracy: 0.7232 1664/3595 [============>.................] - ETA: 1s - loss: 0.8025 - accuracy: 0.7272 1792/3595 [=============>................] - ETA: 0s - loss: 0.8064 - accuracy: 0.7238 1920/3595 [===============>..............] - ETA: 0s - loss: 0.8024 - accuracy: 0.7255 2048/3595 [================>.............] - ETA: 0s - loss: 0.7934 - accuracy: 0.7310 2176/3595 [=================>............] - ETA: 0s - loss: 0.8035 - accuracy: 0.7256 2304/3595 [==================>...........] - ETA: 0s - loss: 0.7960 - accuracy: 0.7253 2432/3595 [===================>..........] - ETA: 0s - loss: 0.7915 - accuracy: 0.7262 2560/3595 [====================>.........] - ETA: 0s - loss: 0.7937 - accuracy: 0.7277 2688/3595 [=====================>........] - ETA: 0s - loss: 0.7911 - accuracy: 0.7284 2816/3595 [======================>.......] - ETA: 0s - loss: 0.7910 - accuracy: 0.7269 2912/3595 [=======================>......] - ETA: 0s - loss: 0.7928 - accuracy: 0.7260 3040/3595 [========================>.....] - ETA: 0s - loss: 0.7984 - accuracy: 0.7227 3168/3595 [=========================>....] - ETA: 0s - loss: 0.7971 - accuracy: 0.7232 3296/3595 [==========================>...] - ETA: 0s - loss: 0.7967 - accuracy: 0.7242 3424/3595 [===========================>..] - ETA: 0s - loss: 0.7958 - accuracy: 0.7252 3552/3595 [============================>.] - ETA: 0s - loss: 0.7995 - accuracy: 0.7233 3595/3595 [==============================] - 2s 543us/sample - loss: 0.8011 - accuracy: 0.7224 - val_loss: 1.0429 - val_accuracy: 0.6263 Epoch 22/28 32/3595 [..............................] - ETA: 1s - loss: 0.7517 - accuracy: 0.6562 160/3595 [>.............................] - ETA: 2s - loss: 0.6472 - accuracy: 0.7750 288/3595 [=>............................] - ETA: 1s - loss: 0.6280 - accuracy: 0.7951 416/3595 [==>...........................] - ETA: 1s - loss: 0.6468 - accuracy: 0.7812 544/3595 [===>..........................] - ETA: 1s - loss: 0.6762 - accuracy: 0.7702 640/3595 [====>.........................] - ETA: 1s - loss: 0.6989 - accuracy: 0.7594 768/3595 [=====>........................] - ETA: 1s - loss: 0.7089 - accuracy: 0.7513 896/3595 [======>.......................] - ETA: 1s - loss: 0.7224 - accuracy: 0.7467 1024/3595 [=======>......................] - ETA: 1s - loss: 0.7296 - accuracy: 0.7412 1152/3595 [========>.....................] - ETA: 1s - loss: 0.7462 - accuracy: 0.7352 1248/3595 [=========>....................] - ETA: 1s - loss: 0.7489 - accuracy: 0.7340 1376/3595 [==========>...................] - ETA: 1s - loss: 0.7510 - accuracy: 0.7340 1504/3595 [===========>..................] - ETA: 1s - loss: 0.7706 - accuracy: 0.7234 1632/3595 [============>.................] - ETA: 1s - loss: 0.7721 - accuracy: 0.7212 1728/3595 [=============>................] - ETA: 0s - loss: 0.7704 - accuracy: 0.7216 1856/3595 [==============>...............] - ETA: 0s - loss: 0.7641 - accuracy: 0.7225 1984/3595 [===============>..............] - ETA: 0s - loss: 0.7737 - accuracy: 0.7193 2112/3595 [================>.............] - ETA: 0s - loss: 0.7745 - accuracy: 0.7197 2208/3595 [=================>............] - ETA: 0s - loss: 0.7784 - accuracy: 0.7178 2336/3595 [==================>...........] - ETA: 0s - loss: 0.7767 - accuracy: 0.7200 2464/3595 [===================>..........] - ETA: 0s - loss: 0.7806 - accuracy: 0.7188 2592/3595 [====================>.........] - ETA: 0s - loss: 0.7868 - accuracy: 0.7160 2688/3595 [=====================>........] - ETA: 0s - loss: 0.7863 - accuracy: 0.7161 2816/3595 [======================>.......] - ETA: 0s - loss: 0.7910 - accuracy: 0.7159 2944/3595 [=======================>......] - ETA: 0s - loss: 0.7956 - accuracy: 0.7143 3072/3595 [========================>.....] - ETA: 0s - loss: 0.7959 - accuracy: 0.7145 3168/3595 [=========================>....] - ETA: 0s - loss: 0.7909 - accuracy: 0.7156 3296/3595 [==========================>...] - ETA: 0s - loss: 0.7932 - accuracy: 0.7160 3424/3595 [===========================>..] - ETA: 0s - loss: 0.7866 - accuracy: 0.7167 3552/3595 [============================>.] - ETA: 0s - loss: 0.7877 - accuracy: 0.7162 3595/3595 [==============================] - 2s 556us/sample - loss: 0.7897 - accuracy: 0.7149 - val_loss: 1.0165 - val_accuracy: 0.6307 Epoch 23/28 32/3595 [..............................] - ETA: 1s - loss: 0.7559 - accuracy: 0.5938 160/3595 [>.............................] - ETA: 2s - loss: 0.6963 - accuracy: 0.7375 288/3595 [=>............................] - ETA: 1s - loss: 0.7239 - accuracy: 0.7396 416/3595 [==>...........................] - ETA: 1s - loss: 0.7540 - accuracy: 0.7212 544/3595 [===>..........................] - ETA: 1s - loss: 0.7855 - accuracy: 0.7114 640/3595 [====>.........................] - ETA: 1s - loss: 0.7850 - accuracy: 0.7172 768/3595 [=====>........................] - ETA: 1s - loss: 0.7568 - accuracy: 0.7305 896/3595 [======>.......................] - ETA: 1s - loss: 0.7755 - accuracy: 0.7277 1024/3595 [=======>......................] - ETA: 1s - loss: 0.7754 - accuracy: 0.7275 1152/3595 [========>.....................] - ETA: 1s - loss: 0.7778 - accuracy: 0.7257 1280/3595 [=========>....................] - ETA: 1s - loss: 0.7689 - accuracy: 0.7281 1376/3595 [==========>...................] - ETA: 1s - loss: 0.7756 - accuracy: 0.7209 1504/3595 [===========>..................] - ETA: 1s - loss: 0.7668 - accuracy: 0.7281 1600/3595 [============>.................] - ETA: 1s - loss: 0.7715 - accuracy: 0.7287 1728/3595 [=============>................] - ETA: 1s - loss: 0.7627 - accuracy: 0.7315 1856/3595 [==============>...............] - ETA: 0s - loss: 0.7603 - accuracy: 0.7338 1984/3595 [===============>..............] - ETA: 0s - loss: 0.7594 - accuracy: 0.7344 2112/3595 [================>.............] - ETA: 0s - loss: 0.7613 - accuracy: 0.7325 2240/3595 [=================>............] - ETA: 0s - loss: 0.7538 - accuracy: 0.7344 2336/3595 [==================>...........] - ETA: 0s - loss: 0.7509 - accuracy: 0.7367 2432/3595 [===================>..........] - ETA: 0s - loss: 0.7524 - accuracy: 0.7356 2528/3595 [====================>.........] - ETA: 0s - loss: 0.7519 - accuracy: 0.7350 2656/3595 [=====================>........] - ETA: 0s - loss: 0.7510 - accuracy: 0.7334 2752/3595 [=====================>........] - ETA: 0s - loss: 0.7535 - accuracy: 0.7318 2880/3595 [=======================>......] - ETA: 0s - loss: 0.7536 - accuracy: 0.7316 3008/3595 [========================>.....] - ETA: 0s - loss: 0.7555 - accuracy: 0.7301 3136/3595 [=========================>....] - ETA: 0s - loss: 0.7532 - accuracy: 0.7312 3232/3595 [=========================>....] - ETA: 0s - loss: 0.7534 - accuracy: 0.7293 3360/3595 [===========================>..] - ETA: 0s - loss: 0.7560 - accuracy: 0.7268 3488/3595 [============================>.] - ETA: 0s - loss: 0.7538 - accuracy: 0.7282 3595/3595 [==============================] - 2s 582us/sample - loss: 0.7524 - accuracy: 0.7296 - val_loss: 1.0162 - val_accuracy: 0.6352 Epoch 24/28 32/3595 [..............................] - ETA: 1s - loss: 0.6079 - accuracy: 0.7812 128/3595 [>.............................] - ETA: 2s - loss: 0.7750 - accuracy: 0.7266 256/3595 [=>............................] - ETA: 1s - loss: 0.7519 - accuracy: 0.7461 384/3595 [==>...........................] - ETA: 1s - loss: 0.7327 - accuracy: 0.7500 480/3595 [===>..........................] - ETA: 1s - loss: 0.7433 - accuracy: 0.7458 608/3595 [====>.........................] - ETA: 1s - loss: 0.7235 - accuracy: 0.7549 736/3595 [=====>........................] - ETA: 1s - loss: 0.7227 - accuracy: 0.7514 832/3595 [=====>........................] - ETA: 1s - loss: 0.7365 - accuracy: 0.7440 960/3595 [=======>......................] - ETA: 1s - loss: 0.7282 - accuracy: 0.7510 1088/3595 [========>.....................] - ETA: 1s - loss: 0.7239 - accuracy: 0.7509 1216/3595 [=========>....................] - ETA: 1s - loss: 0.7298 - accuracy: 0.7492 1344/3595 [==========>...................] - ETA: 1s - loss: 0.7203 - accuracy: 0.7552 1472/3595 [===========>..................] - ETA: 1s - loss: 0.7172 - accuracy: 0.7527 1568/3595 [============>.................] - ETA: 1s - loss: 0.7188 - accuracy: 0.7532 1696/3595 [=============>................] - ETA: 1s - loss: 0.7086 - accuracy: 0.7588 1824/3595 [==============>...............] - ETA: 0s - loss: 0.7173 - accuracy: 0.7549 1952/3595 [===============>..............] - ETA: 0s - loss: 0.7088 - accuracy: 0.7597 2080/3595 [================>.............] - ETA: 0s - loss: 0.7088 - accuracy: 0.7591 2176/3595 [=================>............] - ETA: 0s - loss: 0.7088 - accuracy: 0.7601 2304/3595 [==================>...........] - ETA: 0s - loss: 0.7104 - accuracy: 0.7609 2432/3595 [===================>..........] - ETA: 0s - loss: 0.7129 - accuracy: 0.7603 2528/3595 [====================>.........] - ETA: 0s - loss: 0.7130 - accuracy: 0.7599 2656/3595 [=====================>........] - ETA: 0s - loss: 0.7213 - accuracy: 0.7583 2784/3595 [======================>.......] - ETA: 0s - loss: 0.7306 - accuracy: 0.7557 2912/3595 [=======================>......] - ETA: 0s - loss: 0.7287 - accuracy: 0.7558 3040/3595 [========================>.....] - ETA: 0s - loss: 0.7346 - accuracy: 0.7536 3136/3595 [=========================>....] - ETA: 0s - loss: 0.7318 - accuracy: 0.7548 3264/3595 [==========================>...] - ETA: 0s - loss: 0.7291 - accuracy: 0.7555 3392/3595 [===========================>..] - ETA: 0s - loss: 0.7320 - accuracy: 0.7541 3520/3595 [============================>.] - ETA: 0s - loss: 0.7365 - accuracy: 0.7511 3595/3595 [==============================] - 2s 561us/sample - loss: 0.7361 - accuracy: 0.7527 - val_loss: 1.0226 - val_accuracy: 0.6352 Epoch 25/28 32/3595 [..............................] - ETA: 1s - loss: 0.5936 - accuracy: 0.7812 160/3595 [>.............................] - ETA: 1s - loss: 0.5985 - accuracy: 0.7875 256/3595 [=>............................] - ETA: 1s - loss: 0.6103 - accuracy: 0.7891 384/3595 [==>...........................] - ETA: 1s - loss: 0.6719 - accuracy: 0.7578 512/3595 [===>..........................] - ETA: 1s - loss: 0.6563 - accuracy: 0.7656 640/3595 [====>.........................] - ETA: 1s - loss: 0.6579 - accuracy: 0.7672 768/3595 [=====>........................] - ETA: 1s - loss: 0.6736 - accuracy: 0.7630 896/3595 [======>.......................] - ETA: 1s - loss: 0.6862 - accuracy: 0.7578 1024/3595 [=======>......................] - ETA: 1s - loss: 0.6988 - accuracy: 0.7529 1120/3595 [========>.....................] - ETA: 1s - loss: 0.7055 - accuracy: 0.7536 1248/3595 [=========>....................] - ETA: 1s - loss: 0.7150 - accuracy: 0.7476 1376/3595 [==========>...................] - ETA: 1s - loss: 0.7197 - accuracy: 0.7427 1504/3595 [===========>..................] - ETA: 1s - loss: 0.7188 - accuracy: 0.7453 1632/3595 [============>.................] - ETA: 1s - loss: 0.7151 - accuracy: 0.7469 1760/3595 [=============>................] - ETA: 0s - loss: 0.7067 - accuracy: 0.7500 1888/3595 [==============>...............] - ETA: 0s - loss: 0.6984 - accuracy: 0.7511 2016/3595 [===============>..............] - ETA: 0s - loss: 0.6999 - accuracy: 0.7525 2144/3595 [================>.............] - ETA: 0s - loss: 0.7004 - accuracy: 0.7514 2272/3595 [=================>............] - ETA: 0s - loss: 0.7054 - accuracy: 0.7496 2400/3595 [===================>..........] - ETA: 0s - loss: 0.7030 - accuracy: 0.7513 2528/3595 [====================>.........] - ETA: 0s - loss: 0.7003 - accuracy: 0.7504 2656/3595 [=====================>........] - ETA: 0s - loss: 0.7019 - accuracy: 0.7481 2784/3595 [======================>.......] - ETA: 0s - loss: 0.6989 - accuracy: 0.7489 2912/3595 [=======================>......] - ETA: 0s - loss: 0.6999 - accuracy: 0.7490 3008/3595 [========================>.....] - ETA: 0s - loss: 0.7025 - accuracy: 0.7470 3136/3595 [=========================>....] - ETA: 0s - loss: 0.6990 - accuracy: 0.7497 3264/3595 [==========================>...] - ETA: 0s - loss: 0.7008 - accuracy: 0.7485 3392/3595 [===========================>..] - ETA: 0s - loss: 0.6999 - accuracy: 0.7473 3488/3595 [============================>.] - ETA: 0s - loss: 0.7056 - accuracy: 0.7463 3595/3595 [==============================] - 2s 556us/sample - loss: 0.7087 - accuracy: 0.7458 - val_loss: 0.9949 - val_accuracy: 0.6418 Epoch 26/28 32/3595 [..............................] - ETA: 3s - loss: 0.5226 - accuracy: 0.8125 160/3595 [>.............................] - ETA: 2s - loss: 0.6587 - accuracy: 0.7500 256/3595 [=>............................] - ETA: 2s - loss: 0.6393 - accuracy: 0.7695 352/3595 [=>............................] - ETA: 2s - loss: 0.6374 - accuracy: 0.7727 480/3595 [===>..........................] - ETA: 1s - loss: 0.6830 - accuracy: 0.7604 608/3595 [====>.........................] - ETA: 1s - loss: 0.6914 - accuracy: 0.7599 736/3595 [=====>........................] - ETA: 1s - loss: 0.6896 - accuracy: 0.7609 832/3595 [=====>........................] - ETA: 1s - loss: 0.6924 - accuracy: 0.7620 928/3595 [======>.......................] - ETA: 1s - loss: 0.7043 - accuracy: 0.7554 1024/3595 [=======>......................] - ETA: 1s - loss: 0.7080 - accuracy: 0.7520 1120/3595 [========>.....................] - ETA: 1s - loss: 0.7057 - accuracy: 0.7509 1248/3595 [=========>....................] - ETA: 1s - loss: 0.6946 - accuracy: 0.7588 1376/3595 [==========>...................] - ETA: 1s - loss: 0.6914 - accuracy: 0.7616 1472/3595 [===========>..................] - ETA: 1s - loss: 0.6842 - accuracy: 0.7643 1600/3595 [============>.................] - ETA: 1s - loss: 0.6755 - accuracy: 0.7669 1728/3595 [=============>................] - ETA: 1s - loss: 0.6695 - accuracy: 0.7674 1856/3595 [==============>...............] - ETA: 0s - loss: 0.6663 - accuracy: 0.7678 1984/3595 [===============>..............] - ETA: 0s - loss: 0.6638 - accuracy: 0.7681 2112/3595 [================>.............] - ETA: 0s - loss: 0.6719 - accuracy: 0.7623 2240/3595 [=================>............] - ETA: 0s - loss: 0.6710 - accuracy: 0.7625 2368/3595 [==================>...........] - ETA: 0s - loss: 0.6654 - accuracy: 0.7652 2496/3595 [===================>..........] - ETA: 0s - loss: 0.6651 - accuracy: 0.7652 2624/3595 [====================>.........] - ETA: 0s - loss: 0.6772 - accuracy: 0.7630 2752/3595 [=====================>........] - ETA: 0s - loss: 0.6771 - accuracy: 0.7649 2848/3595 [======================>.......] - ETA: 0s - loss: 0.6805 - accuracy: 0.7630 2976/3595 [=======================>......] - ETA: 0s - loss: 0.6815 - accuracy: 0.7621 3104/3595 [========================>.....] - ETA: 0s - loss: 0.6775 - accuracy: 0.7642 3232/3595 [=========================>....] - ETA: 0s - loss: 0.6795 - accuracy: 0.7624 3360/3595 [===========================>..] - ETA: 0s - loss: 0.6850 - accuracy: 0.7619 3488/3595 [============================>.] - ETA: 0s - loss: 0.6870 - accuracy: 0.7618 3595/3595 [==============================] - 2s 565us/sample - loss: 0.6884 - accuracy: 0.7619 - val_loss: 1.0042 - val_accuracy: 0.6385 Epoch 27/28 32/3595 [..............................] - ETA: 3s - loss: 0.6956 - accuracy: 0.8438 160/3595 [>.............................] - ETA: 2s - loss: 0.6551 - accuracy: 0.7937 288/3595 [=>............................] - ETA: 1s - loss: 0.6522 - accuracy: 0.7812 384/3595 [==>...........................] - ETA: 1s - loss: 0.6173 - accuracy: 0.7917 512/3595 [===>..........................] - ETA: 1s - loss: 0.6054 - accuracy: 0.7969 640/3595 [====>.........................] - ETA: 1s - loss: 0.6123 - accuracy: 0.7937 736/3595 [=====>........................] - ETA: 1s - loss: 0.6143 - accuracy: 0.7935 864/3595 [======>.......................] - ETA: 1s - loss: 0.6222 - accuracy: 0.7824 960/3595 [=======>......................] - ETA: 1s - loss: 0.6255 - accuracy: 0.7781 1088/3595 [========>.....................] - ETA: 1s - loss: 0.6440 - accuracy: 0.7702 1216/3595 [=========>....................] - ETA: 1s - loss: 0.6469 - accuracy: 0.7706 1344/3595 [==========>...................] - ETA: 1s - loss: 0.6473 - accuracy: 0.7716 1440/3595 [===========>..................] - ETA: 1s - loss: 0.6465 - accuracy: 0.7736 1568/3595 [============>.................] - ETA: 1s - loss: 0.6472 - accuracy: 0.7736 1696/3595 [=============>................] - ETA: 1s - loss: 0.6472 - accuracy: 0.7771 1824/3595 [==============>...............] - ETA: 0s - loss: 0.6555 - accuracy: 0.7763 1920/3595 [===============>..............] - ETA: 0s - loss: 0.6511 - accuracy: 0.7792 2048/3595 [================>.............] - ETA: 0s - loss: 0.6537 - accuracy: 0.7778 2176/3595 [=================>............] - ETA: 0s - loss: 0.6543 - accuracy: 0.7790 2304/3595 [==================>...........] - ETA: 0s - loss: 0.6551 - accuracy: 0.7778 2400/3595 [===================>..........] - ETA: 0s - loss: 0.6559 - accuracy: 0.7771 2528/3595 [====================>.........] - ETA: 0s - loss: 0.6567 - accuracy: 0.7773 2656/3595 [=====================>........] - ETA: 0s - loss: 0.6612 - accuracy: 0.7748 2784/3595 [======================>.......] - ETA: 0s - loss: 0.6624 - accuracy: 0.7755 2880/3595 [=======================>......] - ETA: 0s - loss: 0.6608 - accuracy: 0.7760 3008/3595 [========================>.....] - ETA: 0s - loss: 0.6629 - accuracy: 0.7749 3136/3595 [=========================>....] - ETA: 0s - loss: 0.6666 - accuracy: 0.7730 3264/3595 [==========================>...] - ETA: 0s - loss: 0.6677 - accuracy: 0.7714 3360/3595 [===========================>..] - ETA: 0s - loss: 0.6689 - accuracy: 0.7711 3488/3595 [============================>.] - ETA: 0s - loss: 0.6676 - accuracy: 0.7715 3595/3595 [==============================] - 2s 561us/sample - loss: 0.6678 - accuracy: 0.7705 - val_loss: 0.9877 - val_accuracy: 0.6507 Epoch 28/28 32/3595 [..............................] - ETA: 1s - loss: 0.4828 - accuracy: 0.8750 160/3595 [>.............................] - ETA: 1s - loss: 0.5903 - accuracy: 0.8188 288/3595 [=>............................] - ETA: 1s - loss: 0.6470 - accuracy: 0.7882 416/3595 [==>...........................] - ETA: 1s - loss: 0.6364 - accuracy: 0.7909 512/3595 [===>..........................] - ETA: 1s - loss: 0.6338 - accuracy: 0.7871 640/3595 [====>.........................] - ETA: 1s - loss: 0.6367 - accuracy: 0.7828 768/3595 [=====>........................] - ETA: 1s - loss: 0.6450 - accuracy: 0.7826 896/3595 [======>.......................] - ETA: 1s - loss: 0.6648 - accuracy: 0.7712 992/3595 [=======>......................] - ETA: 1s - loss: 0.6499 - accuracy: 0.7812 1120/3595 [========>.....................] - ETA: 1s - loss: 0.6499 - accuracy: 0.7786 1248/3595 [=========>....................] - ETA: 1s - loss: 0.6552 - accuracy: 0.7788 1376/3595 [==========>...................] - ETA: 1s - loss: 0.6542 - accuracy: 0.7791 1472/3595 [===========>..................] - ETA: 1s - loss: 0.6529 - accuracy: 0.7792 1600/3595 [============>.................] - ETA: 1s - loss: 0.6532 - accuracy: 0.7794 1728/3595 [=============>................] - ETA: 0s - loss: 0.6470 - accuracy: 0.7801 1856/3595 [==============>...............] - ETA: 0s - loss: 0.6501 - accuracy: 0.7780 1952/3595 [===============>..............] - ETA: 0s - loss: 0.6520 - accuracy: 0.7766 2080/3595 [================>.............] - ETA: 0s - loss: 0.6494 - accuracy: 0.7769 2208/3595 [=================>............] - ETA: 0s - loss: 0.6520 - accuracy: 0.7745 2336/3595 [==================>...........] - ETA: 0s - loss: 0.6467 - accuracy: 0.7783 2464/3595 [===================>..........] - ETA: 0s - loss: 0.6496 - accuracy: 0.7780 2560/3595 [====================>.........] - ETA: 0s - loss: 0.6517 - accuracy: 0.7762 2688/3595 [=====================>........] - ETA: 0s - loss: 0.6510 - accuracy: 0.7760 2784/3595 [======================>.......] - ETA: 0s - loss: 0.6515 - accuracy: 0.7762 2912/3595 [=======================>......] - ETA: 0s - loss: 0.6556 - accuracy: 0.7747 3040/3595 [========================>.....] - ETA: 0s - loss: 0.6569 - accuracy: 0.7734 3168/3595 [=========================>....] - ETA: 0s - loss: 0.6552 - accuracy: 0.7743 3264/3595 [==========================>...] - ETA: 0s - loss: 0.6566 - accuracy: 0.7748 3392/3595 [===========================>..] - ETA: 0s - loss: 0.6548 - accuracy: 0.7751 3488/3595 [============================>.] - ETA: 0s - loss: 0.6538 - accuracy: 0.7747 3595/3595 [==============================] - 2s 569us/sample - loss: 0.6552 - accuracy: 0.7719 - val_loss: 1.0039 - val_accuracy: 0.6418 Evaluating model for iteration 4... 1498/1498 - 0s - loss: 0.9647 - accuracy: 0.6562 Accuracy for iteration 4 0.6562082767486572
You can run the "python eval.py logs/fcnn1/FCNN1_060422_124733.json 5" in the terminal of Pycharm.(Warning: the right Virtual environment should be venv_python3.6) And you will get result as below shown.
Or you can directly run ! python eval.py logs/fcnn1/FCNN1_060422_124733.json 5 in the jupyter notebook
! python eval.py logs/fcnn1/FCNN1_060422_124733.json 5
Training model for iteration 0... Train on 6993 samples, validate on 1978 samples Epoch 1/48 128/6993 [..............................] - ETA: 18s - loss: 2.3378 - accuracy: 0.0859 2688/6993 [==========>...................] - ETA: 0s - loss: 1.8244 - accuracy: 0.3776 5504/6993 [======================>.......] - ETA: 0s - loss: 1.5241 - accuracy: 0.4822 6993/6993 [==============================] - 1s 79us/sample - loss: 1.4335 - accuracy: 0.5117 - val_loss: 1.0045 - val_accuracy: 0.6507
2022-04-11 23:26:45.548693: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll 2022-04-11 23:26:47.491184: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 2022-04-11 23:26:47.495802: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll 2022-04-11 23:26:47.821311: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:26:47.821342: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:26:47.828676: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:26:48.618886: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:26:48.618910: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:26:48.618917: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:26:48.634071: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) WARNING:tensorflow:From D:\Programs\Anaconda_app\envs\comp47650_env\lib\site-packages\tensorflow_core\python\ops\resource_variable_ops.py:1630: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version. Instructions for updating: If using Keras pass *_constraint arguments to layers. 2022-04-11 23:26:49.257033: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll 2022-04-11 23:26:58.882883: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:26:58.882915: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:26:58.893330: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:26:58.930828: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:26:58.930853: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:26:58.939522: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:26:58.939632: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:26:58.939646: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:26:58.939653: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:26:58.947224: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) 2022-04-11 23:26:59.291812: W tensorflow/python/util/util.cc:299] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them.
Epoch 2/48 128/6993 [..............................] - ETA: 0s - loss: 0.8426 - accuracy: 0.7109 2304/6993 [========>.....................] - ETA: 0s - loss: 0.9052 - accuracy: 0.6897 4864/6993 [===================>..........] - ETA: 0s - loss: 0.8892 - accuracy: 0.6970 6993/6993 [==============================] - 0s 29us/sample - loss: 0.8736 - accuracy: 0.7036 - val_loss: 0.7842 - val_accuracy: 0.7295 Epoch 3/48 128/6993 [..............................] - ETA: 0s - loss: 0.7665 - accuracy: 0.7734 2688/6993 [==========>...................] - ETA: 0s - loss: 0.7080 - accuracy: 0.7653 4992/6993 [====================>.........] - ETA: 0s - loss: 0.6993 - accuracy: 0.7706 6993/6993 [==============================] - 0s 27us/sample - loss: 0.6841 - accuracy: 0.7728 - val_loss: 0.7120 - val_accuracy: 0.7528 Epoch 4/48 128/6993 [..............................] - ETA: 0s - loss: 0.5680 - accuracy: 0.8359 2432/6993 [=========>....................] - ETA: 0s - loss: 0.5936 - accuracy: 0.8084 5248/6993 [=====================>........] - ETA: 0s - loss: 0.5716 - accuracy: 0.8144 6993/6993 [==============================] - 0s 27us/sample - loss: 0.5685 - accuracy: 0.8134 - val_loss: 0.6153 - val_accuracy: 0.7927 Epoch 5/48 128/6993 [..............................] - ETA: 0s - loss: 0.3627 - accuracy: 0.8906 3072/6993 [============>.................] - ETA: 0s - loss: 0.4796 - accuracy: 0.8503 5888/6993 [========================>.....] - ETA: 0s - loss: 0.4759 - accuracy: 0.8478 6993/6993 [==============================] - 0s 27us/sample - loss: 0.4797 - accuracy: 0.8440 - val_loss: 0.5939 - val_accuracy: 0.7927 Epoch 6/48 128/6993 [..............................] - ETA: 0s - loss: 0.5001 - accuracy: 0.8203 2688/6993 [==========>...................] - ETA: 0s - loss: 0.4287 - accuracy: 0.8635 6144/6993 [=========================>....] - ETA: 0s - loss: 0.4221 - accuracy: 0.8636 6993/6993 [==============================] - 0s 22us/sample - loss: 0.4230 - accuracy: 0.8631 - val_loss: 0.5461 - val_accuracy: 0.8129 Epoch 7/48 128/6993 [..............................] - ETA: 0s - loss: 0.3531 - accuracy: 0.8750 3456/6993 [=============>................] - ETA: 0s - loss: 0.3552 - accuracy: 0.8924 6656/6993 [===========================>..] - ETA: 0s - loss: 0.3554 - accuracy: 0.8893 6993/6993 [==============================] - 0s 22us/sample - loss: 0.3566 - accuracy: 0.8886 - val_loss: 0.4880 - val_accuracy: 0.8367 Epoch 8/48 128/6993 [..............................] - ETA: 0s - loss: 0.3219 - accuracy: 0.8828 2304/6993 [========>.....................] - ETA: 0s - loss: 0.2980 - accuracy: 0.9045 5632/6993 [=======================>......] - ETA: 0s - loss: 0.3008 - accuracy: 0.9036 6993/6993 [==============================] - 0s 23us/sample - loss: 0.3046 - accuracy: 0.9012 - val_loss: 0.4754 - val_accuracy: 0.8473 Epoch 9/48 128/6993 [..............................] - ETA: 0s - loss: 0.2536 - accuracy: 0.9219 2816/6993 [===========>..................] - ETA: 0s - loss: 0.2536 - accuracy: 0.9240 5376/6993 [======================>.......] - ETA: 0s - loss: 0.2576 - accuracy: 0.9221 6993/6993 [==============================] - 0s 24us/sample - loss: 0.2575 - accuracy: 0.9222 - val_loss: 0.4506 - val_accuracy: 0.8463 Epoch 10/48 128/6993 [..............................] - ETA: 0s - loss: 0.2394 - accuracy: 0.9297 2816/6993 [===========>..................] - ETA: 0s - loss: 0.2200 - accuracy: 0.9371 6144/6993 [=========================>....] - ETA: 0s - loss: 0.2288 - accuracy: 0.9303 6993/6993 [==============================] - 0s 25us/sample - loss: 0.2298 - accuracy: 0.9294 - val_loss: 0.4229 - val_accuracy: 0.8549 Epoch 11/48 128/6993 [..............................] - ETA: 0s - loss: 0.2571 - accuracy: 0.9297 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1942 - accuracy: 0.9453 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1868 - accuracy: 0.9486 6993/6993 [==============================] - 0s 23us/sample - loss: 0.1889 - accuracy: 0.9459 - val_loss: 0.4129 - val_accuracy: 0.8640 Epoch 12/48 128/6993 [..............................] - ETA: 0s - loss: 0.1374 - accuracy: 0.9609 3328/6993 [=============>................] - ETA: 0s - loss: 0.1583 - accuracy: 0.9558 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1592 - accuracy: 0.9565 6993/6993 [==============================] - 0s 24us/sample - loss: 0.1605 - accuracy: 0.9555 - val_loss: 0.4112 - val_accuracy: 0.8731 Epoch 13/48 128/6993 [..............................] - ETA: 0s - loss: 0.1215 - accuracy: 0.9688 3200/6993 [============>.................] - ETA: 0s - loss: 0.1297 - accuracy: 0.9697 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1364 - accuracy: 0.9663 6993/6993 [==============================] - 0s 22us/sample - loss: 0.1348 - accuracy: 0.9667 - val_loss: 0.4181 - val_accuracy: 0.8680 Epoch 14/48 128/6993 [..............................] - ETA: 0s - loss: 0.1194 - accuracy: 0.9766 3328/6993 [=============>................] - ETA: 0s - loss: 0.1033 - accuracy: 0.9766 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1113 - accuracy: 0.9744 6993/6993 [==============================] - 0s 25us/sample - loss: 0.1112 - accuracy: 0.9743 - val_loss: 0.4034 - val_accuracy: 0.8696 Epoch 15/48 128/6993 [..............................] - ETA: 0s - loss: 0.0861 - accuracy: 0.9922 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0981 - accuracy: 0.9792 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0944 - accuracy: 0.9794 6993/6993 [==============================] - 0s 26us/sample - loss: 0.0945 - accuracy: 0.9793 - val_loss: 0.3824 - val_accuracy: 0.8812 Epoch 16/48 128/6993 [..............................] - ETA: 0s - loss: 0.0569 - accuracy: 1.0000 3328/6993 [=============>................] - ETA: 0s - loss: 0.0720 - accuracy: 0.9892 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0780 - accuracy: 0.9854 6993/6993 [==============================] - 0s 24us/sample - loss: 0.0776 - accuracy: 0.9858 - val_loss: 0.4014 - val_accuracy: 0.8787 Epoch 17/48 128/6993 [..............................] - ETA: 0s - loss: 0.0548 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0686 - accuracy: 0.9885
2022-04-11 23:27:00.203876: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:27:00.203901: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:27:00.211807: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:27:00.211888: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:27:00.211899: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:27:00.211906: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:27:00.222484: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) 2022-04-11 23:27:11.151781: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:27:11.151808: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:27:11.159081: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:27:11.159156: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:27:11.159166: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:27:11.159172: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:27:11.165126: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) 2022-04-11 23:27:22.971110: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:27:22.971137: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:27:22.978797: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:27:22.978894: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:27:22.978905: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:27:22.978911: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:27:22.987604: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) 2022-04-11 23:27:34.718436: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:27:34.718464: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:27:34.724434: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:27:34.724517: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:27:34.724527: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:27:34.724534: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:27:34.730429: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1)
4864/6993 [===================>..........] - ETA: 0s - loss: 0.0697 - accuracy: 0.9877 6993/6993 [==============================] - 0s 25us/sample - loss: 0.0714 - accuracy: 0.9864 - val_loss: 0.3894 - val_accuracy: 0.8822 Epoch 18/48 128/6993 [..............................] - ETA: 0s - loss: 0.0424 - accuracy: 0.9922 3328/6993 [=============>................] - ETA: 0s - loss: 0.0645 - accuracy: 0.9853 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0651 - accuracy: 0.9867 6993/6993 [==============================] - 0s 24us/sample - loss: 0.0654 - accuracy: 0.9868 - val_loss: 0.3942 - val_accuracy: 0.8837 Epoch 19/48 128/6993 [..............................] - ETA: 0s - loss: 0.0471 - accuracy: 1.0000 3200/6993 [============>.................] - ETA: 0s - loss: 0.0484 - accuracy: 0.9931 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0503 - accuracy: 0.9922 6993/6993 [==============================] - 0s 23us/sample - loss: 0.0506 - accuracy: 0.9916 - val_loss: 0.3881 - val_accuracy: 0.8913 Epoch 20/48 128/6993 [..............................] - ETA: 0s - loss: 0.0311 - accuracy: 1.0000 3456/6993 [=============>................] - ETA: 0s - loss: 0.0456 - accuracy: 0.9899 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0438 - accuracy: 0.9920 6993/6993 [==============================] - 0s 25us/sample - loss: 0.0443 - accuracy: 0.9917 - val_loss: 0.3921 - val_accuracy: 0.8857 Epoch 21/48 128/6993 [..............................] - ETA: 0s - loss: 0.0337 - accuracy: 0.9922 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0368 - accuracy: 0.9942 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0361 - accuracy: 0.9943 6993/6993 [==============================] - 0s 25us/sample - loss: 0.0361 - accuracy: 0.9940 - val_loss: 0.3995 - val_accuracy: 0.8842 Epoch 22/48 128/6993 [..............................] - ETA: 0s - loss: 0.0211 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0304 - accuracy: 0.9961 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0300 - accuracy: 0.9970 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0299 - accuracy: 0.9974 - val_loss: 0.3993 - val_accuracy: 0.8923 Epoch 23/48 128/6993 [..............................] - ETA: 0s - loss: 0.0192 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0195 - accuracy: 0.9988 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0209 - accuracy: 0.9986 6993/6993 [==============================] - 0s 31us/sample - loss: 0.0224 - accuracy: 0.9979 - val_loss: 0.4026 - val_accuracy: 0.8852 Epoch 24/48 128/6993 [..............................] - ETA: 0s - loss: 0.0132 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0166 - accuracy: 0.9989 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0185 - accuracy: 0.9988 6993/6993 [==============================] - 0s 25us/sample - loss: 0.0197 - accuracy: 0.9983 - val_loss: 0.3995 - val_accuracy: 0.8898 Epoch 25/48 128/6993 [..............................] - ETA: 0s - loss: 0.0479 - accuracy: 0.9922 3200/6993 [============>.................] - ETA: 0s - loss: 0.0183 - accuracy: 0.9975 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0199 - accuracy: 0.9971 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0201 - accuracy: 0.9971 - val_loss: 0.4128 - val_accuracy: 0.8953 Epoch 26/48 128/6993 [..............................] - ETA: 0s - loss: 0.0187 - accuracy: 0.9922 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0160 - accuracy: 0.9978 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0176 - accuracy: 0.9977 6993/6993 [==============================] - 0s 30us/sample - loss: 0.0187 - accuracy: 0.9977 - val_loss: 0.4170 - val_accuracy: 0.8908 Epoch 27/48 128/6993 [..............................] - ETA: 0s - loss: 0.0091 - accuracy: 1.0000 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0149 - accuracy: 0.9990 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0137 - accuracy: 0.9992 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0148 - accuracy: 0.9989 6993/6993 [==============================] - 0s 31us/sample - loss: 0.0149 - accuracy: 0.9987 - val_loss: 0.4186 - val_accuracy: 0.8948 Epoch 28/48 128/6993 [..............................] - ETA: 0s - loss: 0.0084 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0122 - accuracy: 0.9988 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0129 - accuracy: 0.9989 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0133 - accuracy: 0.9990 - val_loss: 0.4240 - val_accuracy: 0.8918 Epoch 29/48 128/6993 [..............................] - ETA: 0s - loss: 0.0069 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0107 - accuracy: 0.9996 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0147 - accuracy: 0.9982 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0135 - accuracy: 0.9986 - val_loss: 0.4375 - val_accuracy: 0.8918 Epoch 30/48 128/6993 [..............................] - ETA: 0s - loss: 0.0078 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0090 - accuracy: 0.9989 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0123 - accuracy: 0.9984 6993/6993 [==============================] - 0s 26us/sample - loss: 0.0130 - accuracy: 0.9984 - val_loss: 0.4540 - val_accuracy: 0.8888 Epoch 31/48 128/6993 [..............................] - ETA: 0s - loss: 0.0051 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0389 - accuracy: 0.9918 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0263 - accuracy: 0.9951 6993/6993 [==============================] - 0s 25us/sample - loss: 0.0242 - accuracy: 0.9957 - val_loss: 0.4486 - val_accuracy: 0.8918 Epoch 32/48 128/6993 [..............................] - ETA: 0s - loss: 0.0260 - accuracy: 0.9922 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0149 - accuracy: 0.9970 4352/6993 [=================>............] - ETA: 0s - loss: 0.0153 - accuracy: 0.9975 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0207 - accuracy: 0.9962 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0212 - accuracy: 0.9963 - val_loss: 0.5102 - val_accuracy: 0.8711 Epoch 33/48 128/6993 [..............................] - ETA: 0s - loss: 0.0549 - accuracy: 0.9844 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0325 - accuracy: 0.9904 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0373 - accuracy: 0.9898 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0424 - accuracy: 0.9880 - val_loss: 0.5572 - val_accuracy: 0.8650 Epoch 34/48 128/6993 [..............................] - ETA: 0s - loss: 0.0524 - accuracy: 0.9844 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0584 - accuracy: 0.9826 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0580 - accuracy: 0.9808 6912/6993 [============================>.] - ETA: 0s - loss: 0.0528 - accuracy: 0.9831 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0529 - accuracy: 0.9828 - val_loss: 0.5121 - val_accuracy: 0.8822 Epoch 35/48 128/6993 [..............................] - ETA: 0s - loss: 0.0331 - accuracy: 0.9844 3200/6993 [============>.................] - ETA: 0s - loss: 0.0326 - accuracy: 0.9909 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0321 - accuracy: 0.9916 6993/6993 [==============================] - 0s 26us/sample - loss: 0.0329 - accuracy: 0.9910 - val_loss: 0.4856 - val_accuracy: 0.8878 Epoch 36/48 128/6993 [..............................] - ETA: 0s - loss: 0.0829 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0330 - accuracy: 0.9918 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0345 - accuracy: 0.9907 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0337 - accuracy: 0.9907 - val_loss: 0.4691 - val_accuracy: 0.8812 Epoch 37/48 128/6993 [..............................] - ETA: 0s - loss: 0.0071 - accuracy: 1.0000 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0262 - accuracy: 0.9932 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0246 - accuracy: 0.9941 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0239 - accuracy: 0.9937 - val_loss: 0.5256 - val_accuracy: 0.8822 Epoch 38/48 128/6993 [..............................] - ETA: 0s - loss: 0.0298 - accuracy: 0.9922 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0164 - accuracy: 0.9961 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0172 - accuracy: 0.9961 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0160 - accuracy: 0.9963 - val_loss: 0.4974 - val_accuracy: 0.8903 Epoch 39/48 128/6993 [..............................] - ETA: 0s - loss: 0.0214 - accuracy: 0.9922 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0122 - accuracy: 0.9977 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0135 - accuracy: 0.9973 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0134 - accuracy: 0.9973 - val_loss: 0.4736 - val_accuracy: 0.8908 Epoch 40/48 128/6993 [..............................] - ETA: 0s - loss: 0.0149 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0142 - accuracy: 0.9963 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0112 - accuracy: 0.9977 6993/6993 [==============================] - 0s 26us/sample - loss: 0.0109 - accuracy: 0.9979 - val_loss: 0.4642 - val_accuracy: 0.8948 Epoch 41/48 128/6993 [..............................] - ETA: 0s - loss: 0.0306 - accuracy: 0.9922 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0082 - accuracy: 0.9979 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0069 - accuracy: 0.9986 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0069 - accuracy: 0.9987 - val_loss: 0.4662 - val_accuracy: 0.8974 Epoch 42/48 128/6993 [..............................] - ETA: 0s - loss: 0.0072 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0058 - accuracy: 0.9989 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0046 - accuracy: 0.9995 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0044 - accuracy: 0.9994 - val_loss: 0.4697 - val_accuracy: 0.8959 Epoch 43/48 128/6993 [..............................] - ETA: 0s - loss: 0.0034 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0025 - accuracy: 1.0000 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0048 - accuracy: 0.9993 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0046 - accuracy: 0.9993 - val_loss: 0.4805 - val_accuracy: 0.8979 Epoch 44/48 128/6993 [..............................] - ETA: 0s - loss: 0.0199 - accuracy: 0.9922 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0057 - accuracy: 0.9989 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0059 - accuracy: 0.9988 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0056 - accuracy: 0.9989 - val_loss: 0.4873 - val_accuracy: 0.8918 Epoch 45/48 128/6993 [..............................] - ETA: 0s - loss: 0.0033 - accuracy: 1.0000 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0044 - accuracy: 0.9995 4352/6993 [=================>............] - ETA: 0s - loss: 0.0042 - accuracy: 0.9993 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0050 - accuracy: 0.9989 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0049 - accuracy: 0.9990 - val_loss: 0.4822 - val_accuracy: 0.8933 Epoch 46/48 128/6993 [..............................] - ETA: 0s - loss: 0.0029 - accuracy: 1.0000 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0033 - accuracy: 0.9991 4096/6993 [================>.............] - ETA: 0s - loss: 0.0038 - accuracy: 0.9993 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0038 - accuracy: 0.9992 6993/6993 [==============================] - 0s 31us/sample - loss: 0.0051 - accuracy: 0.9990 - val_loss: 0.4866 - val_accuracy: 0.8994 Epoch 47/48 128/6993 [..............................] - ETA: 0s - loss: 0.0034 - accuracy: 1.0000 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0073 - accuracy: 0.9986 4352/6993 [=================>............] - ETA: 0s - loss: 0.0055 - accuracy: 0.9991 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0056 - accuracy: 0.9989 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0055 - accuracy: 0.9989 - val_loss: 0.4808 - val_accuracy: 0.9009 Epoch 48/48 128/6993 [..............................] - ETA: 0s - loss: 0.0017 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0035 - accuracy: 0.9996 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0045 - accuracy: 0.9992 6993/6993 [==============================] - 0s 26us/sample - loss: 0.0040 - accuracy: 0.9993 - val_loss: 0.4837 - val_accuracy: 0.9019 Evaluating model for iteration 0... 1019/1019 - 0s - loss: 0.5335 - accuracy: 0.8842 Accuracy for iteration 0 0.8842002153396606 Training model for iteration 1... Train on 6993 samples, validate on 1978 samples Epoch 1/48 128/6993 [..............................] - ETA: 3s - loss: 2.4033 - accuracy: 0.0391 2048/6993 [=======>......................] - ETA: 0s - loss: 2.0270 - accuracy: 0.2822 4096/6993 [================>.............] - ETA: 0s - loss: 1.7565 - accuracy: 0.3755 6016/6993 [========================>.....] - ETA: 0s - loss: 1.5971 - accuracy: 0.4270 6993/6993 [==============================] - 0s 48us/sample - loss: 1.5330 - accuracy: 0.4523 - val_loss: 1.0759 - val_accuracy: 0.6365 Epoch 2/48 128/6993 [..............................] - ETA: 0s - loss: 0.9616 - accuracy: 0.6719 2048/6993 [=======>......................] - ETA: 0s - loss: 0.9862 - accuracy: 0.6636 4096/6993 [================>.............] - ETA: 0s - loss: 0.9488 - accuracy: 0.6816 6144/6993 [=========================>....] - ETA: 0s - loss: 0.9165 - accuracy: 0.6947 6993/6993 [==============================] - 0s 32us/sample - loss: 0.9031 - accuracy: 0.6983 - val_loss: 0.8165 - val_accuracy: 0.7260 Epoch 3/48 128/6993 [..............................] - ETA: 0s - loss: 0.7750 - accuracy: 0.7109 2432/6993 [=========>....................] - ETA: 0s - loss: 0.7340 - accuracy: 0.7541 5504/6993 [======================>.......] - ETA: 0s - loss: 0.7025 - accuracy: 0.7684 6993/6993 [==============================] - 0s 23us/sample - loss: 0.6885 - accuracy: 0.7723 - val_loss: 0.6870 - val_accuracy: 0.7674 Epoch 4/48 128/6993 [..............................] - ETA: 0s - loss: 0.6764 - accuracy: 0.7734 3072/6993 [============>.................] - ETA: 0s - loss: 0.5620 - accuracy: 0.8164 5888/6993 [========================>.....] - ETA: 0s - loss: 0.5719 - accuracy: 0.8128 6993/6993 [==============================] - 0s 24us/sample - loss: 0.5681 - accuracy: 0.8130 - val_loss: 0.6159 - val_accuracy: 0.7826 Epoch 5/48 128/6993 [..............................] - ETA: 0s - loss: 0.4047 - accuracy: 0.8828 2688/6993 [==========>...................] - ETA: 0s - loss: 0.4878 - accuracy: 0.8478 5760/6993 [=======================>......] - ETA: 0s - loss: 0.4769 - accuracy: 0.8500 6993/6993 [==============================] - 0s 25us/sample - loss: 0.4801 - accuracy: 0.8477 - val_loss: 0.5703 - val_accuracy: 0.8008 Epoch 6/48 128/6993 [..............................] - ETA: 0s - loss: 0.4018 - accuracy: 0.8672 3200/6993 [============>.................] - ETA: 0s - loss: 0.4067 - accuracy: 0.8731 6272/6993 [=========================>....] - ETA: 0s - loss: 0.4093 - accuracy: 0.8713 6993/6993 [==============================] - 0s 22us/sample - loss: 0.4088 - accuracy: 0.8700 - val_loss: 0.5420 - val_accuracy: 0.8074 Epoch 7/48 128/6993 [..............................] - ETA: 0s - loss: 0.4039 - accuracy: 0.8594 3200/6993 [============>.................] - ETA: 0s - loss: 0.3566 - accuracy: 0.8909 6272/6993 [=========================>....] - ETA: 0s - loss: 0.3524 - accuracy: 0.8895 6993/6993 [==============================] - 0s 25us/sample - loss: 0.3499 - accuracy: 0.8906 - val_loss: 0.4848 - val_accuracy: 0.8332 Epoch 8/48 128/6993 [..............................] - ETA: 0s - loss: 0.3123 - accuracy: 0.8906 3200/6993 [============>.................] - ETA: 0s - loss: 0.2845 - accuracy: 0.9181 6272/6993 [=========================>....] - ETA: 0s - loss: 0.2973 - accuracy: 0.9093 6993/6993 [==============================] - 0s 24us/sample - loss: 0.3025 - accuracy: 0.9073 - val_loss: 0.4849 - val_accuracy: 0.8316 Epoch 9/48 128/6993 [..............................] - ETA: 0s - loss: 0.2440 - accuracy: 0.9062 3200/6993 [============>.................] - ETA: 0s - loss: 0.2506 - accuracy: 0.9262 6272/6993 [=========================>....] - ETA: 0s - loss: 0.2526 - accuracy: 0.9243 6993/6993 [==============================] - 0s 23us/sample - loss: 0.2529 - accuracy: 0.9239 - val_loss: 0.4542 - val_accuracy: 0.8443 Epoch 10/48 128/6993 [..............................] - ETA: 0s - loss: 0.2725 - accuracy: 0.9297 3200/6993 [============>.................] - ETA: 0s - loss: 0.2118 - accuracy: 0.9388 6400/6993 [==========================>...] - ETA: 0s - loss: 0.2125 - accuracy: 0.9367 6993/6993 [==============================] - 0s 25us/sample - loss: 0.2110 - accuracy: 0.9375 - val_loss: 0.4257 - val_accuracy: 0.8514 Epoch 11/48 128/6993 [..............................] - ETA: 0s - loss: 0.1209 - accuracy: 1.0000 3072/6993 [============>.................] - ETA: 0s - loss: 0.1736 - accuracy: 0.9567 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1799 - accuracy: 0.9507 6993/6993 [==============================] - 0s 25us/sample - loss: 0.1796 - accuracy: 0.9499 - val_loss: 0.4319 - val_accuracy: 0.8509 Epoch 12/48 128/6993 [..............................] - ETA: 0s - loss: 0.1256 - accuracy: 0.9766 3072/6993 [============>.................] - ETA: 0s - loss: 0.1421 - accuracy: 0.9609 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1511 - accuracy: 0.9590 6993/6993 [==============================] - 0s 22us/sample - loss: 0.1533 - accuracy: 0.9585 - val_loss: 0.4326 - val_accuracy: 0.8589 Epoch 13/48 128/6993 [..............................] - ETA: 0s - loss: 0.1203 - accuracy: 0.9688 3200/6993 [============>.................] - ETA: 0s - loss: 0.1283 - accuracy: 0.9700 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1312 - accuracy: 0.9674 6993/6993 [==============================] - 0s 23us/sample - loss: 0.1325 - accuracy: 0.9654 - val_loss: 0.4207 - val_accuracy: 0.8630 Epoch 14/48 128/6993 [..............................] - ETA: 0s - loss: 0.1628 - accuracy: 0.9531 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1074 - accuracy: 0.9758 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1081 - accuracy: 0.9750 6993/6993 [==============================] - 0s 26us/sample - loss: 0.1070 - accuracy: 0.9755 - val_loss: 0.3913 - val_accuracy: 0.8716 Epoch 15/48 128/6993 [..............................] - ETA: 0s - loss: 0.1242 - accuracy: 0.9766 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1019 - accuracy: 0.9745 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0990 - accuracy: 0.9749 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0991 - accuracy: 0.9750 - val_loss: 0.3989 - val_accuracy: 0.8741 Epoch 16/48 128/6993 [..............................] - ETA: 0s - loss: 0.0662 - accuracy: 1.0000 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0769 - accuracy: 0.9874 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0780 - accuracy: 0.9851 6993/6993 [==============================] - 0s 25us/sample - loss: 0.0766 - accuracy: 0.9854 - val_loss: 0.3893 - val_accuracy: 0.8842 Epoch 17/48 128/6993 [..............................] - ETA: 0s - loss: 0.0524 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0546 - accuracy: 0.9922 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0557 - accuracy: 0.9916 6912/6993 [============================>.] - ETA: 0s - loss: 0.0570 - accuracy: 0.9906 6993/6993 [==============================] - 0s 30us/sample - loss: 0.0569 - accuracy: 0.9906 - val_loss: 0.3910 - val_accuracy: 0.8868 Epoch 18/48 128/6993 [..............................] - ETA: 0s - loss: 0.0554 - accuracy: 0.9922 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0488 - accuracy: 0.9941 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0459 - accuracy: 0.9944 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0456 - accuracy: 0.9944 6993/6993 [==============================] - 0s 36us/sample - loss: 0.0480 - accuracy: 0.9936 - val_loss: 0.3762 - val_accuracy: 0.8847 Epoch 19/48 128/6993 [..............................] - ETA: 0s - loss: 0.0415 - accuracy: 0.9922 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0502 - accuracy: 0.9922 4224/6993 [=================>............] - ETA: 0s - loss: 0.0447 - accuracy: 0.9938 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0429 - accuracy: 0.9939 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0431 - accuracy: 0.9934 - val_loss: 0.3899 - val_accuracy: 0.8847 Epoch 20/48 128/6993 [..............................] - ETA: 0s - loss: 0.0506 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0340 - accuracy: 0.9967 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0359 - accuracy: 0.9959 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0380 - accuracy: 0.9951 - val_loss: 0.4003 - val_accuracy: 0.8868 Epoch 21/48 128/6993 [..............................] - ETA: 0s - loss: 0.0341 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0300 - accuracy: 0.9981 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0304 - accuracy: 0.9969 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0313 - accuracy: 0.9964 - val_loss: 0.3966 - val_accuracy: 0.8878 Epoch 22/48 128/6993 [..............................] - ETA: 0s - loss: 0.0204 - accuracy: 1.0000 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0276 - accuracy: 0.9961 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0274 - accuracy: 0.9958 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0272 - accuracy: 0.9965 6993/6993 [==============================] - 0s 31us/sample - loss: 0.0287 - accuracy: 0.9963 - val_loss: 0.4211 - val_accuracy: 0.8802 Epoch 23/48 128/6993 [..............................] - ETA: 0s - loss: 0.0270 - accuracy: 0.9922 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0264 - accuracy: 0.9959 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0283 - accuracy: 0.9945 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0304 - accuracy: 0.9940 - val_loss: 0.4236 - val_accuracy: 0.8817 Epoch 24/48 128/6993 [..............................] - ETA: 0s - loss: 0.0286 - accuracy: 0.9922 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0316 - accuracy: 0.9932 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0308 - accuracy: 0.9939 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0367 - accuracy: 0.9906 - val_loss: 0.4397 - val_accuracy: 0.8822 Epoch 25/48 128/6993 [..............................] - ETA: 0s - loss: 0.0384 - accuracy: 0.9922 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0341 - accuracy: 0.9918 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0369 - accuracy: 0.9904 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0352 - accuracy: 0.9918 - val_loss: 0.4199 - val_accuracy: 0.8878 Epoch 26/48 128/6993 [..............................] - ETA: 0s - loss: 0.0239 - accuracy: 0.9922 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0216 - accuracy: 0.9979 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0217 - accuracy: 0.9972 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0222 - accuracy: 0.9969 - val_loss: 0.4381 - val_accuracy: 0.8873 Epoch 27/48 128/6993 [..............................] - ETA: 0s - loss: 0.0131 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0126 - accuracy: 1.0000 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0158 - accuracy: 0.9976 6993/6993 [==============================] - 0s 26us/sample - loss: 0.0192 - accuracy: 0.9964 - val_loss: 0.4275 - val_accuracy: 0.8893 Epoch 28/48 128/6993 [..............................] - ETA: 0s - loss: 0.0097 - accuracy: 1.0000 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0113 - accuracy: 0.9989 4352/6993 [=================>............] - ETA: 0s - loss: 0.0127 - accuracy: 0.9984 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0143 - accuracy: 0.9980 - val_loss: 0.4256 - val_accuracy: 0.8913 Epoch 29/48 128/6993 [..............................] - ETA: 0s - loss: 0.0081 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0124 - accuracy: 0.9972 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0116 - accuracy: 0.9979 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0121 - accuracy: 0.9979 - val_loss: 0.4220 - val_accuracy: 0.8908 Epoch 30/48 128/6993 [..............................] - ETA: 0s - loss: 0.0047 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0063 - accuracy: 1.0000 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0072 - accuracy: 0.9996 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0095 - accuracy: 0.9990 - val_loss: 0.4197 - val_accuracy: 0.8979 Epoch 31/48 128/6993 [..............................] - ETA: 0s - loss: 0.0055 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0083 - accuracy: 0.9996 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0094 - accuracy: 0.9986 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0100 - accuracy: 0.9981 - val_loss: 0.4280 - val_accuracy: 0.8943 Epoch 32/48 128/6993 [..............................] - ETA: 0s - loss: 0.0039 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0119 - accuracy: 0.9981 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0112 - accuracy: 0.9976 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0107 - accuracy: 0.9979 - val_loss: 0.4251 - val_accuracy: 0.8953 Epoch 33/48 128/6993 [..............................] - ETA: 0s - loss: 0.0056 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0076 - accuracy: 0.9992 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0080 - accuracy: 0.9989 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0105 - accuracy: 0.9986 - val_loss: 0.4371 - val_accuracy: 0.8923 Epoch 34/48 128/6993 [..............................] - ETA: 0s - loss: 0.0059 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0120 - accuracy: 0.9975 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0120 - accuracy: 0.9980 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0112 - accuracy: 0.9983 - val_loss: 0.4459 - val_accuracy: 0.8923 Epoch 35/48 128/6993 [..............................] - ETA: 0s - loss: 0.0040 - accuracy: 1.0000 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0069 - accuracy: 0.9995 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0067 - accuracy: 0.9990 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0072 - accuracy: 0.9989 - val_loss: 0.4438 - val_accuracy: 0.8953 Epoch 36/48 128/6993 [..............................] - ETA: 0s - loss: 0.0037 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0041 - accuracy: 1.0000 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0056 - accuracy: 0.9994 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0060 - accuracy: 0.9993 - val_loss: 0.4437 - val_accuracy: 0.8943 Epoch 37/48 128/6993 [..............................] - ETA: 0s - loss: 0.0034 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0045 - accuracy: 0.9996 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0052 - accuracy: 0.9993 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0056 - accuracy: 0.9991 - val_loss: 0.4508 - val_accuracy: 0.8943 Epoch 38/48 128/6993 [..............................] - ETA: 0s - loss: 0.0050 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0063 - accuracy: 0.9993 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0074 - accuracy: 0.9985 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0081 - accuracy: 0.9984 - val_loss: 0.4724 - val_accuracy: 0.8862 Epoch 39/48 128/6993 [..............................] - ETA: 0s - loss: 0.0038 - accuracy: 1.0000 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0077 - accuracy: 0.9974 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0066 - accuracy: 0.9984 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0062 - accuracy: 0.9986 - val_loss: 0.4551 - val_accuracy: 0.8938 Epoch 40/48 128/6993 [..............................] - ETA: 0s - loss: 0.0110 - accuracy: 0.9922 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0038 - accuracy: 0.9993 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0053 - accuracy: 0.9987 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0056 - accuracy: 0.9987 - val_loss: 0.4604 - val_accuracy: 0.8933 Epoch 41/48 128/6993 [..............................] - ETA: 0s - loss: 0.0027 - accuracy: 1.0000 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0047 - accuracy: 0.9993 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0051 - accuracy: 0.9993 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0053 - accuracy: 0.9993 - val_loss: 0.4555 - val_accuracy: 0.8933 Epoch 42/48 128/6993 [..............................] - ETA: 0s - loss: 0.0025 - accuracy: 1.0000 3072/6993 [============>.................] - ETA: 0s - loss: 0.0063 - accuracy: 0.9987 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0064 - accuracy: 0.9983 6993/6993 [==============================] - 0s 25us/sample - loss: 0.0059 - accuracy: 0.9986 - val_loss: 0.4711 - val_accuracy: 0.8943 Epoch 43/48 128/6993 [..............................] - ETA: 0s - loss: 0.0017 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0035 - accuracy: 0.9993 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0057 - accuracy: 0.9988 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0054 - accuracy: 0.9989 - val_loss: 0.4776 - val_accuracy: 0.8908 Epoch 44/48 128/6993 [..............................] - ETA: 0s - loss: 0.0023 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0027 - accuracy: 0.9996 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0054 - accuracy: 0.9989 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0046 - accuracy: 0.9993 - val_loss: 0.4720 - val_accuracy: 0.8933 Epoch 45/48 128/6993 [..............................] - ETA: 0s - loss: 0.0029 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0075 - accuracy: 0.9981 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0081 - accuracy: 0.9977 6912/6993 [============================>.] - ETA: 0s - loss: 0.0063 - accuracy: 0.9984 6993/6993 [==============================] - 0s 36us/sample - loss: 0.0063 - accuracy: 0.9984 - val_loss: 0.4743 - val_accuracy: 0.8953 Epoch 46/48 128/6993 [..............................] - ETA: 0s - loss: 0.0021 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0019 - accuracy: 1.0000 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0042 - accuracy: 0.9994 6993/6993 [==============================] - 0s 30us/sample - loss: 0.0055 - accuracy: 0.9990 - val_loss: 0.4894 - val_accuracy: 0.8928 Epoch 47/48 128/6993 [..............................] - ETA: 0s - loss: 0.0013 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0040 - accuracy: 0.9996 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0046 - accuracy: 0.9993 6993/6993 [==============================] - 0s 26us/sample - loss: 0.0051 - accuracy: 0.9990 - val_loss: 0.4806 - val_accuracy: 0.8948 Epoch 48/48 128/6993 [..............................] - ETA: 0s - loss: 7.7664e-04 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0069 - accuracy: 0.9981 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0050 - accuracy: 0.9987 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0060 - accuracy: 0.9989 - val_loss: 0.4971 - val_accuracy: 0.8903 Evaluating model for iteration 1... 1019/1019 - 0s - loss: 0.5504 - accuracy: 0.8832 Accuracy for iteration 1 0.8832188248634338 Training model for iteration 2... Train on 6993 samples, validate on 1978 samples Epoch 1/48 128/6993 [..............................] - ETA: 4s - loss: 2.3681 - accuracy: 0.0781 2688/6993 [==========>...................] - ETA: 0s - loss: 1.8558 - accuracy: 0.3635 4864/6993 [===================>..........] - ETA: 0s - loss: 1.6140 - accuracy: 0.4463 6993/6993 [==============================] - 0s 49us/sample - loss: 1.4651 - accuracy: 0.4942 - val_loss: 1.0538 - val_accuracy: 0.6355 Epoch 2/48 128/6993 [..............................] - ETA: 0s - loss: 0.8755 - accuracy: 0.7266 2688/6993 [==========>...................] - ETA: 0s - loss: 0.9505 - accuracy: 0.6722 4864/6993 [===================>..........] - ETA: 0s - loss: 0.9175 - accuracy: 0.6842 6993/6993 [==============================] - 0s 27us/sample - loss: 0.8924 - accuracy: 0.6934 - val_loss: 0.8234 - val_accuracy: 0.7194 Epoch 3/48 128/6993 [..............................] - ETA: 0s - loss: 0.7240 - accuracy: 0.7578 2304/6993 [========>.....................] - ETA: 0s - loss: 0.7114 - accuracy: 0.7721 5120/6993 [====================>.........] - ETA: 0s - loss: 0.7091 - accuracy: 0.7727 6993/6993 [==============================] - 0s 29us/sample - loss: 0.6949 - accuracy: 0.7715 - val_loss: 0.7372 - val_accuracy: 0.7427 Epoch 4/48 128/6993 [..............................] - ETA: 0s - loss: 0.6137 - accuracy: 0.8125 2560/6993 [=========>....................] - ETA: 0s - loss: 0.6148 - accuracy: 0.7953 5248/6993 [=====================>........] - ETA: 0s - loss: 0.6000 - accuracy: 0.8022 6993/6993 [==============================] - 0s 27us/sample - loss: 0.5887 - accuracy: 0.8037 - val_loss: 0.6294 - val_accuracy: 0.7826 Epoch 5/48 128/6993 [..............................] - ETA: 0s - loss: 0.5728 - accuracy: 0.7812 2304/6993 [========>.....................] - ETA: 0s - loss: 0.5100 - accuracy: 0.8281 4992/6993 [====================>.........] - ETA: 0s - loss: 0.5103 - accuracy: 0.8303 6993/6993 [==============================] - 0s 29us/sample - loss: 0.5052 - accuracy: 0.8314 - val_loss: 0.5959 - val_accuracy: 0.7907 Epoch 6/48 128/6993 [..............................] - ETA: 0s - loss: 0.4680 - accuracy: 0.8438 2560/6993 [=========>....................] - ETA: 0s - loss: 0.4469 - accuracy: 0.8574 4736/6993 [===================>..........] - ETA: 0s - loss: 0.4368 - accuracy: 0.8596 6993/6993 [==============================] - 0s 29us/sample - loss: 0.4294 - accuracy: 0.8603 - val_loss: 0.5519 - val_accuracy: 0.8074 Epoch 7/48 128/6993 [..............................] - ETA: 0s - loss: 0.4182 - accuracy: 0.8359 2816/6993 [===========>..................] - ETA: 0s - loss: 0.3634 - accuracy: 0.8842 5632/6993 [=======================>......] - ETA: 0s - loss: 0.3693 - accuracy: 0.8835 6993/6993 [==============================] - 0s 28us/sample - loss: 0.3688 - accuracy: 0.8827 - val_loss: 0.4940 - val_accuracy: 0.8352 Epoch 8/48 128/6993 [..............................] - ETA: 0s - loss: 0.3474 - accuracy: 0.8906 2560/6993 [=========>....................] - ETA: 0s - loss: 0.3155 - accuracy: 0.9066 5248/6993 [=====================>........] - ETA: 0s - loss: 0.3161 - accuracy: 0.9047 6993/6993 [==============================] - 0s 28us/sample - loss: 0.3168 - accuracy: 0.9042 - val_loss: 0.4973 - val_accuracy: 0.8316 Epoch 9/48 128/6993 [..............................] - ETA: 0s - loss: 0.3683 - accuracy: 0.8516 2048/6993 [=======>......................] - ETA: 0s - loss: 0.2869 - accuracy: 0.9131 4608/6993 [==================>...........] - ETA: 0s - loss: 0.2803 - accuracy: 0.9117 6993/6993 [==============================] - 0s 27us/sample - loss: 0.2768 - accuracy: 0.9126 - val_loss: 0.4480 - val_accuracy: 0.8544 Epoch 10/48 128/6993 [..............................] - ETA: 0s - loss: 0.3091 - accuracy: 0.9297 2176/6993 [========>.....................] - ETA: 0s - loss: 0.2202 - accuracy: 0.9375 4096/6993 [================>.............] - ETA: 0s - loss: 0.2239 - accuracy: 0.9346 5376/6993 [======================>.......] - ETA: 0s - loss: 0.2257 - accuracy: 0.9330 6993/6993 [==============================] - 0s 36us/sample - loss: 0.2294 - accuracy: 0.9325 - val_loss: 0.4355 - val_accuracy: 0.8504 Epoch 11/48 128/6993 [..............................] - ETA: 0s - loss: 0.2328 - accuracy: 0.9453 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1900 - accuracy: 0.9484 4352/6993 [=================>............] - ETA: 0s - loss: 0.1942 - accuracy: 0.9460 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1956 - accuracy: 0.9470 6993/6993 [==============================] - 0s 29us/sample - loss: 0.1919 - accuracy: 0.9481 - val_loss: 0.4199 - val_accuracy: 0.8589 Epoch 12/48 128/6993 [..............................] - ETA: 0s - loss: 0.1516 - accuracy: 0.9609 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1600 - accuracy: 0.9570 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1656 - accuracy: 0.9556 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1696 - accuracy: 0.9530 6993/6993 [==============================] - 0s 29us/sample - loss: 0.1694 - accuracy: 0.9532 - val_loss: 0.4322 - val_accuracy: 0.8564 Epoch 13/48 128/6993 [..............................] - ETA: 0s - loss: 0.1174 - accuracy: 0.9766 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1192 - accuracy: 0.9731 4352/6993 [=================>............] - ETA: 0s - loss: 0.1291 - accuracy: 0.9690 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1386 - accuracy: 0.9650 6993/6993 [==============================] - 0s 30us/sample - loss: 0.1398 - accuracy: 0.9638 - val_loss: 0.4126 - val_accuracy: 0.8691 Epoch 14/48 128/6993 [..............................] - ETA: 0s - loss: 0.1144 - accuracy: 0.9688 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1121 - accuracy: 0.9756 4224/6993 [=================>............] - ETA: 0s - loss: 0.1160 - accuracy: 0.9728 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1158 - accuracy: 0.9731 6993/6993 [==============================] - 0s 32us/sample - loss: 0.1168 - accuracy: 0.9724 - val_loss: 0.4082 - val_accuracy: 0.8711 Epoch 15/48 128/6993 [..............................] - ETA: 0s - loss: 0.0908 - accuracy: 0.9922 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0889 - accuracy: 0.9832 3072/6993 [============>.................] - ETA: 0s - loss: 0.1015 - accuracy: 0.9798 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0965 - accuracy: 0.9810 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1008 - accuracy: 0.9779 6993/6993 [==============================] - 0s 40us/sample - loss: 0.1004 - accuracy: 0.9783 - val_loss: 0.4059 - val_accuracy: 0.8721 Epoch 16/48 128/6993 [..............................] - ETA: 0s - loss: 0.0647 - accuracy: 1.0000 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0730 - accuracy: 0.9867 4352/6993 [=================>............] - ETA: 0s - loss: 0.0764 - accuracy: 0.9855 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0814 - accuracy: 0.9841 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0822 - accuracy: 0.9837 - val_loss: 0.4294 - val_accuracy: 0.8670 Epoch 17/48 128/6993 [..............................] - ETA: 0s - loss: 0.0781 - accuracy: 0.9766 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0747 - accuracy: 0.9844 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0711 - accuracy: 0.9850 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0748 - accuracy: 0.9833 - val_loss: 0.4082 - val_accuracy: 0.8756 Epoch 18/48 128/6993 [..............................] - ETA: 0s - loss: 0.0473 - accuracy: 1.0000 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0549 - accuracy: 0.9907 4096/6993 [================>.............] - ETA: 0s - loss: 0.0615 - accuracy: 0.9890 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0673 - accuracy: 0.9868 6993/6993 [==============================] - 0s 34us/sample - loss: 0.0664 - accuracy: 0.9868 - val_loss: 0.4308 - val_accuracy: 0.8741 Epoch 19/48 128/6993 [..............................] - ETA: 0s - loss: 0.0526 - accuracy: 0.9844 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0444 - accuracy: 0.9940 4224/6993 [=================>............] - ETA: 0s - loss: 0.0453 - accuracy: 0.9938 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0508 - accuracy: 0.9917 6993/6993 [==============================] - 0s 32us/sample - loss: 0.0511 - accuracy: 0.9911 - val_loss: 0.4264 - val_accuracy: 0.8802 Epoch 20/48 128/6993 [..............................] - ETA: 0s - loss: 0.0573 - accuracy: 0.9766 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0433 - accuracy: 0.9935 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0416 - accuracy: 0.9939 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0414 - accuracy: 0.9937 - val_loss: 0.4100 - val_accuracy: 0.8792 Epoch 21/48 128/6993 [..............................] - ETA: 0s - loss: 0.0255 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0329 - accuracy: 0.9971 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0340 - accuracy: 0.9972 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0334 - accuracy: 0.9971 - val_loss: 0.4235 - val_accuracy: 0.8842 Epoch 22/48 128/6993 [..............................] - ETA: 0s - loss: 0.0217 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0254 - accuracy: 0.9985 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0274 - accuracy: 0.9980 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0282 - accuracy: 0.9976 - val_loss: 0.4293 - val_accuracy: 0.8842 Epoch 23/48 128/6993 [..............................] - ETA: 0s - loss: 0.0256 - accuracy: 1.0000 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0215 - accuracy: 0.9991 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0238 - accuracy: 0.9977 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0247 - accuracy: 0.9970 - val_loss: 0.4298 - val_accuracy: 0.8787 Epoch 24/48 128/6993 [..............................] - ETA: 0s - loss: 0.0150 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0204 - accuracy: 0.9985 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0205 - accuracy: 0.9987 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0205 - accuracy: 0.9986 - val_loss: 0.4365 - val_accuracy: 0.8842 Epoch 25/48 128/6993 [..............................] - ETA: 0s - loss: 0.0128 - accuracy: 1.0000 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0199 - accuracy: 0.9968 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0183 - accuracy: 0.9975 6993/6993 [==============================] - 0s 31us/sample - loss: 0.0188 - accuracy: 0.9977 - val_loss: 0.4382 - val_accuracy: 0.8857 Epoch 26/48 128/6993 [..............................] - ETA: 0s - loss: 0.0123 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0140 - accuracy: 0.9988 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0159 - accuracy: 0.9983 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0160 - accuracy: 0.9984 - val_loss: 0.4357 - val_accuracy: 0.8857 Epoch 27/48 128/6993 [..............................] - ETA: 0s - loss: 0.0181 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0155 - accuracy: 0.9985 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0153 - accuracy: 0.9980 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0145 - accuracy: 0.9983 - val_loss: 0.4507 - val_accuracy: 0.8868 Epoch 28/48 128/6993 [..............................] - ETA: 0s - loss: 0.0120 - accuracy: 1.0000 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0121 - accuracy: 0.9990 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0137 - accuracy: 0.9984 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0136 - accuracy: 0.9986 - val_loss: 0.4573 - val_accuracy: 0.8888 Epoch 29/48 128/6993 [..............................] - ETA: 0s - loss: 0.0061 - accuracy: 1.0000 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0085 - accuracy: 1.0000 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0102 - accuracy: 0.9990 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0107 - accuracy: 0.9990 - val_loss: 0.4541 - val_accuracy: 0.8888 Epoch 30/48 128/6993 [..............................] - ETA: 0s - loss: 0.0071 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0122 - accuracy: 0.9980 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0130 - accuracy: 0.9982 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0128 - accuracy: 0.9981 - val_loss: 0.4564 - val_accuracy: 0.8857 Epoch 31/48 128/6993 [..............................] - ETA: 0s - loss: 0.0113 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0239 - accuracy: 0.9953 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0249 - accuracy: 0.9937 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0223 - accuracy: 0.9949 - val_loss: 0.4681 - val_accuracy: 0.8837 Epoch 32/48 128/6993 [..............................] - ETA: 0s - loss: 0.0070 - accuracy: 1.0000 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0155 - accuracy: 0.9974 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0145 - accuracy: 0.9977 6912/6993 [============================>.] - ETA: 0s - loss: 0.0139 - accuracy: 0.9978 6993/6993 [==============================] - 0s 31us/sample - loss: 0.0138 - accuracy: 0.9979 - val_loss: 0.5176 - val_accuracy: 0.8777 Epoch 33/48 128/6993 [..............................] - ETA: 0s - loss: 0.0105 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1097 - accuracy: 0.9699 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1462 - accuracy: 0.9559 6993/6993 [==============================] - 0s 31us/sample - loss: 0.1581 - accuracy: 0.9507 - val_loss: 0.6808 - val_accuracy: 0.8458 Epoch 34/48 128/6993 [..............................] - ETA: 0s - loss: 0.1402 - accuracy: 0.9531 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1349 - accuracy: 0.9553 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1173 - accuracy: 0.9613 6993/6993 [==============================] - 0s 29us/sample - loss: 0.1091 - accuracy: 0.9641 - val_loss: 0.4790 - val_accuracy: 0.8812 Epoch 35/48 128/6993 [..............................] - ETA: 0s - loss: 0.0631 - accuracy: 0.9766 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0443 - accuracy: 0.9855 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0384 - accuracy: 0.9896 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0375 - accuracy: 0.9903 - val_loss: 0.4677 - val_accuracy: 0.8847 Epoch 36/48 128/6993 [..............................] - ETA: 0s - loss: 0.0129 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0152 - accuracy: 0.9975 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0154 - accuracy: 0.9980 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0170 - accuracy: 0.9977 - val_loss: 0.4472 - val_accuracy: 0.8903 Epoch 37/48 128/6993 [..............................] - ETA: 0s - loss: 0.0060 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0205 - accuracy: 0.9967 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0177 - accuracy: 0.9969 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0163 - accuracy: 0.9971 - val_loss: 0.4555 - val_accuracy: 0.8862 Epoch 38/48 128/6993 [..............................] - ETA: 0s - loss: 0.0049 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0069 - accuracy: 0.9988 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0078 - accuracy: 0.9989 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0084 - accuracy: 0.9987 - val_loss: 0.4522 - val_accuracy: 0.8857 Epoch 39/48 128/6993 [..............................] - ETA: 0s - loss: 0.0040 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0077 - accuracy: 0.9989 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0072 - accuracy: 0.9989 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0079 - accuracy: 0.9987 - val_loss: 0.4544 - val_accuracy: 0.8913 Epoch 40/48 128/6993 [..............................] - ETA: 0s - loss: 0.0030 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0065 - accuracy: 0.9988 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0062 - accuracy: 0.9991 6784/6993 [============================>.] - ETA: 0s - loss: 0.0060 - accuracy: 0.9990 6993/6993 [==============================] - 0s 34us/sample - loss: 0.0059 - accuracy: 0.9990 - val_loss: 0.4588 - val_accuracy: 0.8933 Epoch 41/48 128/6993 [..............................] - ETA: 0s - loss: 0.0032 - accuracy: 1.0000 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0038 - accuracy: 0.9995 4352/6993 [=================>............] - ETA: 0s - loss: 0.0060 - accuracy: 0.9991 6912/6993 [============================>.] - ETA: 0s - loss: 0.0065 - accuracy: 0.9987 6993/6993 [==============================] - 0s 31us/sample - loss: 0.0065 - accuracy: 0.9987 - val_loss: 0.4787 - val_accuracy: 0.8898 Epoch 42/48 128/6993 [..............................] - ETA: 0s - loss: 0.0052 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0099 - accuracy: 0.9981 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0085 - accuracy: 0.9985 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0076 - accuracy: 0.9989 - val_loss: 0.4628 - val_accuracy: 0.8893 Epoch 43/48 128/6993 [..............................] - ETA: 0s - loss: 0.0018 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0039 - accuracy: 0.9992 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0051 - accuracy: 0.9990 6993/6993 [==============================] - 0s 31us/sample - loss: 0.0051 - accuracy: 0.9990 - val_loss: 0.4680 - val_accuracy: 0.8948 Epoch 44/48 128/6993 [..............................] - ETA: 0s - loss: 0.0025 - accuracy: 1.0000 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0044 - accuracy: 0.9991 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0048 - accuracy: 0.9992 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0053 - accuracy: 0.9991 - val_loss: 0.4663 - val_accuracy: 0.8918 Epoch 45/48 128/6993 [..............................] - ETA: 0s - loss: 0.0027 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0030 - accuracy: 1.0000 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0054 - accuracy: 0.9990 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0056 - accuracy: 0.9989 - val_loss: 0.4711 - val_accuracy: 0.8938 Epoch 46/48 128/6993 [..............................] - ETA: 0s - loss: 0.0273 - accuracy: 0.9922 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0042 - accuracy: 0.9992 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0046 - accuracy: 0.9990 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0048 - accuracy: 0.9990 - val_loss: 0.4737 - val_accuracy: 0.8933 Epoch 47/48 128/6993 [..............................] - ETA: 0s - loss: 0.0024 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0050 - accuracy: 0.9992 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0045 - accuracy: 0.9992 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0047 - accuracy: 0.9991 - val_loss: 0.4750 - val_accuracy: 0.8933 Epoch 48/48 128/6993 [..............................] - ETA: 0s - loss: 0.0015 - accuracy: 1.0000 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0023 - accuracy: 0.9997 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0027 - accuracy: 0.9995 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0037 - accuracy: 0.9990 - val_loss: 0.5009 - val_accuracy: 0.8898 Evaluating model for iteration 2... 1019/1019 - 0s - loss: 0.5620 - accuracy: 0.8881 Accuracy for iteration 2 0.8881255984306335 Training model for iteration 3... Train on 6993 samples, validate on 1978 samples Epoch 1/48 128/6993 [..............................] - ETA: 4s - loss: 2.3293 - accuracy: 0.1250 2560/6993 [=========>....................] - ETA: 0s - loss: 1.8722 - accuracy: 0.3750 5376/6993 [======================>.......] - ETA: 0s - loss: 1.5603 - accuracy: 0.4691 6993/6993 [==============================] - 0s 53us/sample - loss: 1.4516 - accuracy: 0.5055 - val_loss: 1.0474 - val_accuracy: 0.6431 Epoch 2/48 128/6993 [..............................] - ETA: 0s - loss: 0.9671 - accuracy: 0.7266 2688/6993 [==========>...................] - ETA: 0s - loss: 0.9249 - accuracy: 0.6968 5504/6993 [======================>.......] - ETA: 0s - loss: 0.8827 - accuracy: 0.7055 6993/6993 [==============================] - 0s 29us/sample - loss: 0.8644 - accuracy: 0.7137 - val_loss: 0.8143 - val_accuracy: 0.7209 Epoch 3/48 128/6993 [..............................] - ETA: 0s - loss: 0.6210 - accuracy: 0.8047 2176/6993 [========>.....................] - ETA: 0s - loss: 0.7165 - accuracy: 0.7449 4224/6993 [=================>............] - ETA: 0s - loss: 0.7069 - accuracy: 0.7590 6272/6993 [=========================>....] - ETA: 0s - loss: 0.6842 - accuracy: 0.7695 6993/6993 [==============================] - 0s 30us/sample - loss: 0.6784 - accuracy: 0.7725 - val_loss: 0.7160 - val_accuracy: 0.7533 Epoch 4/48 128/6993 [..............................] - ETA: 0s - loss: 0.5707 - accuracy: 0.8047 2304/6993 [========>.....................] - ETA: 0s - loss: 0.5739 - accuracy: 0.8034 4736/6993 [===================>..........] - ETA: 0s - loss: 0.5692 - accuracy: 0.8114 6784/6993 [============================>.] - ETA: 0s - loss: 0.5720 - accuracy: 0.8094 6993/6993 [==============================] - 0s 29us/sample - loss: 0.5676 - accuracy: 0.8102 - val_loss: 0.6442 - val_accuracy: 0.7765 Epoch 5/48 128/6993 [..............................] - ETA: 0s - loss: 0.4683 - accuracy: 0.8359 2560/6993 [=========>....................] - ETA: 0s - loss: 0.4838 - accuracy: 0.8406 5376/6993 [======================>.......] - ETA: 0s - loss: 0.4789 - accuracy: 0.8410 6993/6993 [==============================] - 0s 26us/sample - loss: 0.4777 - accuracy: 0.8403 - val_loss: 0.5864 - val_accuracy: 0.7942 Epoch 6/48 128/6993 [..............................] - ETA: 0s - loss: 0.2745 - accuracy: 0.9297 2816/6993 [===========>..................] - ETA: 0s - loss: 0.4028 - accuracy: 0.8746 5632/6993 [=======================>......] - ETA: 0s - loss: 0.4015 - accuracy: 0.8752 6993/6993 [==============================] - 0s 30us/sample - loss: 0.4043 - accuracy: 0.8736 - val_loss: 0.5391 - val_accuracy: 0.8160 Epoch 7/48 128/6993 [..............................] - ETA: 0s - loss: 0.4087 - accuracy: 0.8516 2560/6993 [=========>....................] - ETA: 0s - loss: 0.3236 - accuracy: 0.9031 5376/6993 [======================>.......] - ETA: 0s - loss: 0.3392 - accuracy: 0.8930 6993/6993 [==============================] - 0s 27us/sample - loss: 0.3425 - accuracy: 0.8909 - val_loss: 0.4958 - val_accuracy: 0.8246 Epoch 8/48 128/6993 [..............................] - ETA: 0s - loss: 0.3119 - accuracy: 0.9141 2816/6993 [===========>..................] - ETA: 0s - loss: 0.2930 - accuracy: 0.9048 5632/6993 [=======================>......] - ETA: 0s - loss: 0.2943 - accuracy: 0.9086 6993/6993 [==============================] - 0s 29us/sample - loss: 0.2951 - accuracy: 0.9069 - val_loss: 0.5038 - val_accuracy: 0.8311 Epoch 9/48 128/6993 [..............................] - ETA: 0s - loss: 0.2194 - accuracy: 0.9141 2048/6993 [=======>......................] - ETA: 0s - loss: 0.2581 - accuracy: 0.9233 3840/6993 [===============>..............] - ETA: 0s - loss: 0.2517 - accuracy: 0.9268 5888/6993 [========================>.....] - ETA: 0s - loss: 0.2563 - accuracy: 0.9231 6993/6993 [==============================] - 0s 34us/sample - loss: 0.2541 - accuracy: 0.9228 - val_loss: 0.4639 - val_accuracy: 0.8372 Epoch 10/48 128/6993 [..............................] - ETA: 0s - loss: 0.2345 - accuracy: 0.9141 1920/6993 [=======>......................] - ETA: 0s - loss: 0.2179 - accuracy: 0.9349 4864/6993 [===================>..........] - ETA: 0s - loss: 0.2116 - accuracy: 0.9396 6993/6993 [==============================] - 0s 29us/sample - loss: 0.2110 - accuracy: 0.9385 - val_loss: 0.4325 - val_accuracy: 0.8539 Epoch 11/48 128/6993 [..............................] - ETA: 0s - loss: 0.1595 - accuracy: 0.9609 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1839 - accuracy: 0.9515 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1812 - accuracy: 0.9486 6993/6993 [==============================] - 0s 30us/sample - loss: 0.1843 - accuracy: 0.9471 - val_loss: 0.4275 - val_accuracy: 0.8620 Epoch 12/48 128/6993 [..............................] - ETA: 0s - loss: 0.1367 - accuracy: 0.9766 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1396 - accuracy: 0.9644 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1434 - accuracy: 0.9609 6993/6993 [==============================] - 0s 31us/sample - loss: 0.1524 - accuracy: 0.9572 - val_loss: 0.4258 - val_accuracy: 0.8610 Epoch 13/48 128/6993 [..............................] - ETA: 0s - loss: 0.0942 - accuracy: 0.9844 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1214 - accuracy: 0.9727 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1248 - accuracy: 0.9683 6993/6993 [==============================] - 0s 29us/sample - loss: 0.1262 - accuracy: 0.9680 - val_loss: 0.4128 - val_accuracy: 0.8716 Epoch 14/48 128/6993 [..............................] - ETA: 0s - loss: 0.0576 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0903 - accuracy: 0.9815 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0999 - accuracy: 0.9776 6993/6993 [==============================] - 0s 29us/sample - loss: 0.1036 - accuracy: 0.9754 - val_loss: 0.4067 - val_accuracy: 0.8751 Epoch 15/48 128/6993 [..............................] - ETA: 0s - loss: 0.0583 - accuracy: 0.9922 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0827 - accuracy: 0.9814 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0835 - accuracy: 0.9818 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0843 - accuracy: 0.9817 - val_loss: 0.4110 - val_accuracy: 0.8686 Epoch 16/48 128/6993 [..............................] - ETA: 0s - loss: 0.1171 - accuracy: 0.9531 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0738 - accuracy: 0.9836 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0690 - accuracy: 0.9855 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0697 - accuracy: 0.9857 - val_loss: 0.3973 - val_accuracy: 0.8802 Epoch 17/48 128/6993 [..............................] - ETA: 0s - loss: 0.0326 - accuracy: 1.0000 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0598 - accuracy: 0.9917 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0584 - accuracy: 0.9898 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0585 - accuracy: 0.9898 - val_loss: 0.4078 - val_accuracy: 0.8807 Epoch 18/48 128/6993 [..............................] - ETA: 0s - loss: 0.0538 - accuracy: 0.9766 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0484 - accuracy: 0.9911 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0496 - accuracy: 0.9920 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0497 - accuracy: 0.9916 - val_loss: 0.4009 - val_accuracy: 0.8847 Epoch 19/48 128/6993 [..............................] - ETA: 0s - loss: 0.0303 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0536 - accuracy: 0.9891 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0527 - accuracy: 0.9901 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0520 - accuracy: 0.9904 - val_loss: 0.4269 - val_accuracy: 0.8731 Epoch 20/48 128/6993 [..............................] - ETA: 0s - loss: 0.0477 - accuracy: 0.9844 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0400 - accuracy: 0.9943 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0403 - accuracy: 0.9947 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0399 - accuracy: 0.9944 - val_loss: 0.4315 - val_accuracy: 0.8802 Epoch 21/48 128/6993 [..............................] - ETA: 0s - loss: 0.0395 - accuracy: 0.9844 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0316 - accuracy: 0.9963 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0346 - accuracy: 0.9951 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0352 - accuracy: 0.9947 - val_loss: 0.4150 - val_accuracy: 0.8862 Epoch 22/48 128/6993 [..............................] - ETA: 0s - loss: 0.0279 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0263 - accuracy: 0.9961 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0268 - accuracy: 0.9962 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0251 - accuracy: 0.9969 - val_loss: 0.4293 - val_accuracy: 0.8817 Epoch 23/48 128/6993 [..............................] - ETA: 0s - loss: 0.0173 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0197 - accuracy: 0.9989 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0218 - accuracy: 0.9979 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0214 - accuracy: 0.9979 - val_loss: 0.4131 - val_accuracy: 0.8827 Epoch 24/48 128/6993 [..............................] - ETA: 0s - loss: 0.0216 - accuracy: 0.9922 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0161 - accuracy: 0.9984 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0198 - accuracy: 0.9975 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0199 - accuracy: 0.9971 - val_loss: 0.4265 - val_accuracy: 0.8862 Epoch 25/48 128/6993 [..............................] - ETA: 0s - loss: 0.0145 - accuracy: 1.0000 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0184 - accuracy: 0.9982 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0193 - accuracy: 0.9974 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0191 - accuracy: 0.9974 - val_loss: 0.4495 - val_accuracy: 0.8817 Epoch 26/48 128/6993 [..............................] - ETA: 0s - loss: 0.0124 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0187 - accuracy: 0.9973 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0189 - accuracy: 0.9966 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0198 - accuracy: 0.9966 - val_loss: 0.4325 - val_accuracy: 0.8883 Epoch 27/48 128/6993 [..............................] - ETA: 0s - loss: 0.0150 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0173 - accuracy: 0.9979 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0181 - accuracy: 0.9979 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0176 - accuracy: 0.9980 - val_loss: 0.4452 - val_accuracy: 0.8873 Epoch 28/48 128/6993 [..............................] - ETA: 0s - loss: 0.0123 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0121 - accuracy: 0.9988 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0129 - accuracy: 0.9982 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0143 - accuracy: 0.9979 - val_loss: 0.4371 - val_accuracy: 0.8888 Epoch 29/48 128/6993 [..............................] - ETA: 0s - loss: 0.0065 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0123 - accuracy: 0.9985 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0126 - accuracy: 0.9982 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0117 - accuracy: 0.9986 - val_loss: 0.4328 - val_accuracy: 0.8913 Epoch 30/48 128/6993 [..............................] - ETA: 0s - loss: 0.0213 - accuracy: 0.9922 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0079 - accuracy: 0.9996 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0100 - accuracy: 0.9982 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0110 - accuracy: 0.9981 - val_loss: 0.4426 - val_accuracy: 0.8913 Epoch 31/48 128/6993 [..............................] - ETA: 0s - loss: 0.0079 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0110 - accuracy: 0.9978 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0112 - accuracy: 0.9982 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0109 - accuracy: 0.9983 - val_loss: 0.4443 - val_accuracy: 0.8928 Epoch 32/48 128/6993 [..............................] - ETA: 0s - loss: 0.0046 - accuracy: 1.0000 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0082 - accuracy: 0.9991 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0094 - accuracy: 0.9982 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0083 - accuracy: 0.9987 - val_loss: 0.4519 - val_accuracy: 0.8903 Epoch 33/48 128/6993 [..............................] - ETA: 0s - loss: 0.0042 - accuracy: 1.0000 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0084 - accuracy: 0.9984 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0083 - accuracy: 0.9987 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0077 - accuracy: 0.9990 - val_loss: 0.4587 - val_accuracy: 0.8908 Epoch 34/48 128/6993 [..............................] - ETA: 0s - loss: 0.0054 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0070 - accuracy: 0.9993 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0087 - accuracy: 0.9984 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0099 - accuracy: 0.9980 - val_loss: 0.4739 - val_accuracy: 0.8903 Epoch 35/48 128/6993 [..............................] - ETA: 0s - loss: 0.0128 - accuracy: 0.9922 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0212 - accuracy: 0.9913 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0299 - accuracy: 0.9889 6912/6993 [============================>.] - ETA: 0s - loss: 0.0331 - accuracy: 0.9878 6993/6993 [==============================] - 0s 34us/sample - loss: 0.0335 - accuracy: 0.9877 - val_loss: 0.6317 - val_accuracy: 0.8569 Epoch 36/48 128/6993 [..............................] - ETA: 0s - loss: 0.0476 - accuracy: 0.9844 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1265 - accuracy: 0.9644 4224/6993 [=================>............] - ETA: 0s - loss: 0.1498 - accuracy: 0.9579 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1626 - accuracy: 0.9524 6993/6993 [==============================] - 0s 31us/sample - loss: 0.1635 - accuracy: 0.9515 - val_loss: 0.4876 - val_accuracy: 0.8787 Epoch 37/48 128/6993 [..............................] - ETA: 0s - loss: 0.0820 - accuracy: 0.9609 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0922 - accuracy: 0.9681 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0798 - accuracy: 0.9727 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0751 - accuracy: 0.9745 - val_loss: 0.4934 - val_accuracy: 0.8777 Epoch 38/48 128/6993 [..............................] - ETA: 0s - loss: 0.0396 - accuracy: 0.9844 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0446 - accuracy: 0.9849 4224/6993 [=================>............] - ETA: 0s - loss: 0.0444 - accuracy: 0.9841 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0462 - accuracy: 0.9844 6993/6993 [==============================] - 0s 32us/sample - loss: 0.0450 - accuracy: 0.9851 - val_loss: 0.4806 - val_accuracy: 0.8857 Epoch 39/48 128/6993 [..............................] - ETA: 0s - loss: 0.0202 - accuracy: 1.0000 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0301 - accuracy: 0.9912 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0278 - accuracy: 0.9924 6993/6993 [==============================] - 0s 30us/sample - loss: 0.0247 - accuracy: 0.9939 - val_loss: 0.4568 - val_accuracy: 0.8908 Epoch 40/48 128/6993 [..............................] - ETA: 0s - loss: 0.0051 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0135 - accuracy: 0.9973 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0116 - accuracy: 0.9978 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0110 - accuracy: 0.9979 - val_loss: 0.4345 - val_accuracy: 0.9039 Epoch 41/48 128/6993 [..............................] - ETA: 0s - loss: 0.0095 - accuracy: 1.0000 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0077 - accuracy: 0.9987 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0078 - accuracy: 0.9988 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0074 - accuracy: 0.9990 - val_loss: 0.4438 - val_accuracy: 0.8979 Epoch 42/48 128/6993 [..............................] - ETA: 0s - loss: 0.0054 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0049 - accuracy: 0.9996 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0059 - accuracy: 0.9993 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0054 - accuracy: 0.9994 - val_loss: 0.4405 - val_accuracy: 0.9024 Epoch 43/48 128/6993 [..............................] - ETA: 0s - loss: 0.0031 - accuracy: 1.0000 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0036 - accuracy: 0.9997 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0041 - accuracy: 0.9996 6993/6993 [==============================] - 0s 31us/sample - loss: 0.0050 - accuracy: 0.9993 - val_loss: 0.4401 - val_accuracy: 0.9034 Epoch 44/48 128/6993 [..............................] - ETA: 0s - loss: 0.0021 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0038 - accuracy: 0.9993 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0046 - accuracy: 0.9991 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0049 - accuracy: 0.9991 - val_loss: 0.4492 - val_accuracy: 0.9009 Epoch 45/48 128/6993 [..............................] - ETA: 0s - loss: 0.0019 - accuracy: 1.0000 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0045 - accuracy: 0.9991 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0047 - accuracy: 0.9990 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0043 - accuracy: 0.9991 - val_loss: 0.4583 - val_accuracy: 0.9044 Epoch 46/48 128/6993 [..............................] - ETA: 0s - loss: 0.0026 - accuracy: 1.0000 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0035 - accuracy: 0.9995 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0050 - accuracy: 0.9988 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0056 - accuracy: 0.9986 - val_loss: 0.4562 - val_accuracy: 0.8994 Epoch 47/48 128/6993 [..............................] - ETA: 0s - loss: 0.0024 - accuracy: 1.0000 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0041 - accuracy: 0.9996 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0048 - accuracy: 0.9988 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0043 - accuracy: 0.9990 - val_loss: 0.4524 - val_accuracy: 0.9044 Epoch 48/48 128/6993 [..............................] - ETA: 0s - loss: 0.0020 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0038 - accuracy: 0.9996 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0037 - accuracy: 0.9994 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0036 - accuracy: 0.9996 - val_loss: 0.4613 - val_accuracy: 0.9014 Evaluating model for iteration 3... 1019/1019 - 0s - loss: 0.5476 - accuracy: 0.9068 Accuracy for iteration 3 0.9067713618278503 Training model for iteration 4... Train on 6993 samples, validate on 1978 samples Epoch 1/48 128/6993 [..............................] - ETA: 4s - loss: 2.3906 - accuracy: 0.1719 1664/6993 [======>.......................] - ETA: 0s - loss: 2.0838 - accuracy: 0.2867 4480/6993 [==================>...........] - ETA: 0s - loss: 1.6820 - accuracy: 0.4183 6912/6993 [============================>.] - ETA: 0s - loss: 1.4967 - accuracy: 0.4800 6993/6993 [==============================] - 0s 54us/sample - loss: 1.4927 - accuracy: 0.4809 - val_loss: 1.0421 - val_accuracy: 0.6441 Epoch 2/48 128/6993 [..............................] - ETA: 0s - loss: 0.8584 - accuracy: 0.7344 2816/6993 [===========>..................] - ETA: 0s - loss: 0.9358 - accuracy: 0.6942 5504/6993 [======================>.......] - ETA: 0s - loss: 0.9109 - accuracy: 0.6973 6993/6993 [==============================] - 0s 29us/sample - loss: 0.8937 - accuracy: 0.7041 - val_loss: 0.8370 - val_accuracy: 0.7189 Epoch 3/48 128/6993 [..............................] - ETA: 0s - loss: 0.7400 - accuracy: 0.7422 2304/6993 [========>.....................] - ETA: 0s - loss: 0.7408 - accuracy: 0.7465 4480/6993 [==================>...........] - ETA: 0s - loss: 0.7094 - accuracy: 0.7618 6144/6993 [=========================>....] - ETA: 0s - loss: 0.6989 - accuracy: 0.7679 6993/6993 [==============================] - 0s 34us/sample - loss: 0.6920 - accuracy: 0.7703 - val_loss: 0.6968 - val_accuracy: 0.7654 Epoch 4/48 128/6993 [..............................] - ETA: 0s - loss: 0.5396 - accuracy: 0.8516 2432/6993 [=========>....................] - ETA: 0s - loss: 0.5739 - accuracy: 0.8125 4608/6993 [==================>...........] - ETA: 0s - loss: 0.5741 - accuracy: 0.8053 6993/6993 [==============================] - 0s 31us/sample - loss: 0.5683 - accuracy: 0.8117 - val_loss: 0.6357 - val_accuracy: 0.7826 Epoch 5/48 128/6993 [..............................] - ETA: 0s - loss: 0.4348 - accuracy: 0.8828 2816/6993 [===========>..................] - ETA: 0s - loss: 0.4888 - accuracy: 0.8448 5632/6993 [=======================>......] - ETA: 0s - loss: 0.4899 - accuracy: 0.8423 6993/6993 [==============================] - 0s 30us/sample - loss: 0.4889 - accuracy: 0.8407 - val_loss: 0.5944 - val_accuracy: 0.7937 Epoch 6/48 128/6993 [..............................] - ETA: 0s - loss: 0.3573 - accuracy: 0.8750 2176/6993 [========>.....................] - ETA: 0s - loss: 0.4292 - accuracy: 0.8626 4480/6993 [==================>...........] - ETA: 0s - loss: 0.4289 - accuracy: 0.8567 6912/6993 [============================>.] - ETA: 0s - loss: 0.4281 - accuracy: 0.8589 6993/6993 [==============================] - 0s 32us/sample - loss: 0.4280 - accuracy: 0.8590 - val_loss: 0.5365 - val_accuracy: 0.8140 Epoch 7/48 128/6993 [..............................] - ETA: 0s - loss: 0.3386 - accuracy: 0.8906 2432/6993 [=========>....................] - ETA: 0s - loss: 0.3520 - accuracy: 0.8865 4992/6993 [====================>.........] - ETA: 0s - loss: 0.3506 - accuracy: 0.8868 6993/6993 [==============================] - 0s 29us/sample - loss: 0.3557 - accuracy: 0.8850 - val_loss: 0.5254 - val_accuracy: 0.8145 Epoch 8/48 128/6993 [..............................] - ETA: 0s - loss: 0.2648 - accuracy: 0.9297 2432/6993 [=========>....................] - ETA: 0s - loss: 0.3137 - accuracy: 0.9030 4608/6993 [==================>...........] - ETA: 0s - loss: 0.3129 - accuracy: 0.9021 6993/6993 [==============================] - 0s 27us/sample - loss: 0.3095 - accuracy: 0.9036 - val_loss: 0.4945 - val_accuracy: 0.8251 Epoch 9/48 128/6993 [..............................] - ETA: 0s - loss: 0.2228 - accuracy: 0.9375 2816/6993 [===========>..................] - ETA: 0s - loss: 0.2674 - accuracy: 0.9201 5632/6993 [=======================>......] - ETA: 0s - loss: 0.2556 - accuracy: 0.9226 6993/6993 [==============================] - 0s 29us/sample - loss: 0.2556 - accuracy: 0.9226 - val_loss: 0.4723 - val_accuracy: 0.8296 Epoch 10/48 128/6993 [..............................] - ETA: 0s - loss: 0.2097 - accuracy: 0.9375 2432/6993 [=========>....................] - ETA: 0s - loss: 0.2359 - accuracy: 0.9289 5120/6993 [====================>.........] - ETA: 0s - loss: 0.2188 - accuracy: 0.9354 6993/6993 [==============================] - 0s 29us/sample - loss: 0.2186 - accuracy: 0.9354 - val_loss: 0.4422 - val_accuracy: 0.8483 Epoch 11/48 128/6993 [..............................] - ETA: 0s - loss: 0.1525 - accuracy: 0.9609 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1828 - accuracy: 0.9512 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1876 - accuracy: 0.9457 6993/6993 [==============================] - 0s 27us/sample - loss: 0.1922 - accuracy: 0.9451 - val_loss: 0.4564 - val_accuracy: 0.8438 Epoch 12/48 128/6993 [..............................] - ETA: 0s - loss: 0.1454 - accuracy: 0.9688 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1590 - accuracy: 0.9544 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1596 - accuracy: 0.9564 6993/6993 [==============================] - 0s 29us/sample - loss: 0.1595 - accuracy: 0.9564 - val_loss: 0.4073 - val_accuracy: 0.8721 Epoch 13/48 128/6993 [..............................] - ETA: 0s - loss: 0.1140 - accuracy: 0.9922 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1281 - accuracy: 0.9702 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1382 - accuracy: 0.9655 6993/6993 [==============================] - 0s 28us/sample - loss: 0.1361 - accuracy: 0.9644 - val_loss: 0.4219 - val_accuracy: 0.8630 Epoch 14/48 128/6993 [..............................] - ETA: 0s - loss: 0.1147 - accuracy: 0.9688 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1158 - accuracy: 0.9757 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1144 - accuracy: 0.9727 6993/6993 [==============================] - 0s 26us/sample - loss: 0.1148 - accuracy: 0.9724 - val_loss: 0.4246 - val_accuracy: 0.8635 Epoch 15/48 128/6993 [..............................] - ETA: 0s - loss: 0.0905 - accuracy: 0.9922 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1040 - accuracy: 0.9749 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1016 - accuracy: 0.9760 6993/6993 [==============================] - 0s 26us/sample - loss: 0.1002 - accuracy: 0.9765 - val_loss: 0.4147 - val_accuracy: 0.8691 Epoch 16/48 128/6993 [..............................] - ETA: 0s - loss: 0.0681 - accuracy: 0.9844 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0747 - accuracy: 0.9857 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0734 - accuracy: 0.9854 6993/6993 [==============================] - 0s 30us/sample - loss: 0.0752 - accuracy: 0.9850 - val_loss: 0.3984 - val_accuracy: 0.8731 Epoch 17/48 128/6993 [..............................] - ETA: 0s - loss: 0.0601 - accuracy: 0.9922 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0647 - accuracy: 0.9877 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0682 - accuracy: 0.9857 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0680 - accuracy: 0.9864 - val_loss: 0.3929 - val_accuracy: 0.8797 Epoch 18/48 128/6993 [..............................] - ETA: 0s - loss: 0.0597 - accuracy: 0.9844 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0536 - accuracy: 0.9917 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0547 - accuracy: 0.9910 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0601 - accuracy: 0.9891 - val_loss: 0.4279 - val_accuracy: 0.8741 Epoch 19/48 128/6993 [..............................] - ETA: 0s - loss: 0.0548 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0486 - accuracy: 0.9914 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0507 - accuracy: 0.9914 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0525 - accuracy: 0.9901 - val_loss: 0.4114 - val_accuracy: 0.8680 Epoch 20/48 128/6993 [..............................] - ETA: 0s - loss: 0.0473 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0472 - accuracy: 0.9918 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0472 - accuracy: 0.9920 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0465 - accuracy: 0.9916 - val_loss: 0.4140 - val_accuracy: 0.8787 Epoch 21/48 128/6993 [..............................] - ETA: 0s - loss: 0.0736 - accuracy: 0.9922 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0369 - accuracy: 0.9950 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0358 - accuracy: 0.9950 6993/6993 [==============================] - 0s 30us/sample - loss: 0.0353 - accuracy: 0.9951 - val_loss: 0.4234 - val_accuracy: 0.8782 Epoch 22/48 128/6993 [..............................] - ETA: 0s - loss: 0.0285 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0265 - accuracy: 0.9981 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0283 - accuracy: 0.9965 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0279 - accuracy: 0.9969 - val_loss: 0.3996 - val_accuracy: 0.8857 Epoch 23/48 128/6993 [..............................] - ETA: 0s - loss: 0.0160 - accuracy: 1.0000 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0198 - accuracy: 0.9983 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0253 - accuracy: 0.9964 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0248 - accuracy: 0.9967 - val_loss: 0.4252 - val_accuracy: 0.8837 Epoch 24/48 128/6993 [..............................] - ETA: 0s - loss: 0.0214 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0183 - accuracy: 0.9988 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0198 - accuracy: 0.9983 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0205 - accuracy: 0.9981 - val_loss: 0.4230 - val_accuracy: 0.8812 Epoch 25/48 128/6993 [..............................] - ETA: 0s - loss: 0.0159 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0167 - accuracy: 0.9989 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0196 - accuracy: 0.9980 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0220 - accuracy: 0.9969 - val_loss: 0.4344 - val_accuracy: 0.8787 Epoch 26/48 128/6993 [..............................] - ETA: 0s - loss: 0.0223 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0149 - accuracy: 0.9986 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0160 - accuracy: 0.9984 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0173 - accuracy: 0.9981 - val_loss: 0.4245 - val_accuracy: 0.8878 Epoch 27/48 128/6993 [..............................] - ETA: 0s - loss: 0.0227 - accuracy: 1.0000 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0173 - accuracy: 0.9971 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0199 - accuracy: 0.9955 6784/6993 [============================>.] - ETA: 0s - loss: 0.0178 - accuracy: 0.9968 6993/6993 [==============================] - 0s 28us/sample - loss: 0.0177 - accuracy: 0.9969 - val_loss: 0.4260 - val_accuracy: 0.8852 Epoch 28/48 128/6993 [..............................] - ETA: 0s - loss: 0.0097 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0118 - accuracy: 0.9996 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0113 - accuracy: 0.9993 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0125 - accuracy: 0.9989 - val_loss: 0.4292 - val_accuracy: 0.8842 Epoch 29/48 128/6993 [..............................] - ETA: 0s - loss: 0.0119 - accuracy: 1.0000 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0099 - accuracy: 0.9989 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0134 - accuracy: 0.9980 6993/6993 [==============================] - 0s 33us/sample - loss: 0.0125 - accuracy: 0.9983 - val_loss: 0.4388 - val_accuracy: 0.8842 Epoch 30/48 128/6993 [..............................] - ETA: 0s - loss: 0.0071 - accuracy: 1.0000 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0111 - accuracy: 0.9982 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0113 - accuracy: 0.9982 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0133 - accuracy: 0.9979 6993/6993 [==============================] - 0s 34us/sample - loss: 0.0138 - accuracy: 0.9977 - val_loss: 0.5129 - val_accuracy: 0.8736 Epoch 31/48 128/6993 [..............................] - ETA: 0s - loss: 0.0375 - accuracy: 0.9844 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0158 - accuracy: 0.9969 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0156 - accuracy: 0.9972 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0148 - accuracy: 0.9976 - val_loss: 0.4669 - val_accuracy: 0.8741 Epoch 32/48 128/6993 [..............................] - ETA: 0s - loss: 0.0094 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0173 - accuracy: 0.9957 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0178 - accuracy: 0.9961 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0176 - accuracy: 0.9961 - val_loss: 0.4803 - val_accuracy: 0.8802 Epoch 33/48 128/6993 [..............................] - ETA: 0s - loss: 0.0320 - accuracy: 0.9922 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0145 - accuracy: 0.9974 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0139 - accuracy: 0.9979 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0125 - accuracy: 0.9984 - val_loss: 0.4625 - val_accuracy: 0.8868 Epoch 34/48 128/6993 [..............................] - ETA: 0s - loss: 0.0060 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0118 - accuracy: 0.9975 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0120 - accuracy: 0.9977 6993/6993 [==============================] - 0s 30us/sample - loss: 0.0114 - accuracy: 0.9977 - val_loss: 0.4809 - val_accuracy: 0.8847 Epoch 35/48 128/6993 [..............................] - ETA: 0s - loss: 0.0108 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0064 - accuracy: 0.9996 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0064 - accuracy: 0.9992 6993/6993 [==============================] - 0s 26us/sample - loss: 0.0079 - accuracy: 0.9987 - val_loss: 0.4840 - val_accuracy: 0.8852 Epoch 36/48 128/6993 [..............................] - ETA: 0s - loss: 0.0095 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0120 - accuracy: 0.9975 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0089 - accuracy: 0.9980 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0085 - accuracy: 0.9981 - val_loss: 0.4774 - val_accuracy: 0.8857 Epoch 37/48 128/6993 [..............................] - ETA: 0s - loss: 0.0041 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0057 - accuracy: 0.9996 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0055 - accuracy: 0.9996 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0063 - accuracy: 0.9990 - val_loss: 0.5007 - val_accuracy: 0.8862 Epoch 38/48 128/6993 [..............................] - ETA: 0s - loss: 0.0065 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0081 - accuracy: 0.9977 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0081 - accuracy: 0.9980 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0081 - accuracy: 0.9984 - val_loss: 0.5052 - val_accuracy: 0.8868 Epoch 39/48 128/6993 [..............................] - ETA: 0s - loss: 0.0288 - accuracy: 0.9922 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0068 - accuracy: 0.9992 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0058 - accuracy: 0.9990 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0074 - accuracy: 0.9987 - val_loss: 0.5313 - val_accuracy: 0.8842 Epoch 40/48 128/6993 [..............................] - ETA: 0s - loss: 0.0099 - accuracy: 1.0000 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0117 - accuracy: 0.9974 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0199 - accuracy: 0.9957 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0397 - accuracy: 0.9893 - val_loss: 0.7139 - val_accuracy: 0.8524 Epoch 41/48 128/6993 [..............................] - ETA: 0s - loss: 0.0891 - accuracy: 0.9609 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1603 - accuracy: 0.9520 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1833 - accuracy: 0.9464 6993/6993 [==============================] - 0s 27us/sample - loss: 0.1760 - accuracy: 0.9472 - val_loss: 0.5485 - val_accuracy: 0.8650 Epoch 42/48 128/6993 [..............................] - ETA: 0s - loss: 0.1523 - accuracy: 0.9062 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0843 - accuracy: 0.9708 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0774 - accuracy: 0.9725 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0708 - accuracy: 0.9754 - val_loss: 0.4931 - val_accuracy: 0.8787 Epoch 43/48 128/6993 [..............................] - ETA: 0s - loss: 0.0191 - accuracy: 0.9922 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0288 - accuracy: 0.9918 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0305 - accuracy: 0.9918 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0266 - accuracy: 0.9930 - val_loss: 0.5077 - val_accuracy: 0.8726 Epoch 44/48 128/6993 [..............................] - ETA: 0s - loss: 0.0251 - accuracy: 0.9844 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0145 - accuracy: 0.9974 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0139 - accuracy: 0.9974 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0164 - accuracy: 0.9970 - val_loss: 0.4634 - val_accuracy: 0.8868 Epoch 45/48 128/6993 [..............................] - ETA: 0s - loss: 0.0105 - accuracy: 1.0000 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0068 - accuracy: 1.0000 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0076 - accuracy: 0.9993 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0092 - accuracy: 0.9986 - val_loss: 0.4653 - val_accuracy: 0.8918 Epoch 46/48 128/6993 [..............................] - ETA: 0s - loss: 0.0037 - accuracy: 1.0000 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0121 - accuracy: 0.9968 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0085 - accuracy: 0.9984 6993/6993 [==============================] - 0s 27us/sample - loss: 0.0079 - accuracy: 0.9986 - val_loss: 0.4497 - val_accuracy: 0.8938 Epoch 47/48 128/6993 [..............................] - ETA: 0s - loss: 0.0082 - accuracy: 1.0000 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0045 - accuracy: 0.9991 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0060 - accuracy: 0.9986 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0066 - accuracy: 0.9986 - val_loss: 0.4590 - val_accuracy: 0.8913 Epoch 48/48 128/6993 [..............................] - ETA: 0s - loss: 0.0024 - accuracy: 1.0000 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0046 - accuracy: 0.9994 4224/6993 [=================>............] - ETA: 0s - loss: 0.0046 - accuracy: 0.9993 6993/6993 [==============================] - 0s 29us/sample - loss: 0.0063 - accuracy: 0.9987 - val_loss: 0.4616 - val_accuracy: 0.8969 Evaluating model for iteration 4... 1019/1019 - 0s - loss: 0.4795 - accuracy: 0.8950 Accuracy for iteration 4 0.8949950933456421
You can run the "python eval.py logs/fcnn2/FCNN2_060422_125313.json 5" in the terminal of Pycharm.(Warning: the right Virtual environment should be venv_python3.6) And you will get result as below shown.
Or you can directly run ! python eval.py logs/fcnn2/FCNN2_060422_125313.json 5 in the jupyter notebook
! python eval.py logs/fcnn2/FCNN2_060422_125313.json 5
Training model for iteration 0... Train on 6993 samples, validate on 1978 samples Epoch 1/199 128/6993 [..............................] - ETA: 32s - loss: 2.3161 - accuracy: 0.0859 768/6993 [==>...........................] - ETA: 5s - loss: 2.2353 - accuracy: 0.1758 1664/6993 [======>.......................] - ETA: 2s - loss: 2.1052 - accuracy: 0.2368 2432/6993 [=========>....................] - ETA: 1s - loss: 2.0308 - accuracy: 0.2578 3072/6993 [============>.................] - ETA: 1s - loss: 1.9687 - accuracy: 0.2816 3840/6993 [===============>..............] - ETA: 0s - loss: 1.9073 - accuracy: 0.3031 4736/6993 [===================>..........] - ETA: 0s - loss: 1.8346 - accuracy: 0.3298 5632/6993 [=======================>......] - ETA: 0s - loss: 1.7844 - accuracy: 0.3478 6272/6993 [=========================>....] - ETA: 0s - loss: 1.7600 - accuracy: 0.3575 6993/6993 [==============================] - 1s 188us/sample - loss: 1.7298 - accuracy: 0.3691 - val_loss: 1.2496 - val_accuracy: 0.5566 Epoch 2/199 128/6993 [..............................] - ETA: 0s - loss: 1.3925 - accuracy: 0.4844 896/6993 [==>...........................] - ETA: 0s - loss: 1.3591 - accuracy: 0.5145 1664/6993 [======>.......................] - ETA: 0s - loss: 1.3520 - accuracy: 0.5096 2560/6993 [=========>....................] - ETA: 0s - loss: 1.3472 - accuracy: 0.5246 3328/6993 [=============>................] - ETA: 0s - loss: 1.3293 - accuracy: 0.5306 4096/6993 [================>.............] - ETA: 0s - loss: 1.3186 - accuracy: 0.5369 4864/6993 [===================>..........] - ETA: 0s - loss: 1.3113 - accuracy: 0.5421 5632/6993 [=======================>......] - ETA: 0s - loss: 1.2981 - accuracy: 0.5478 6272/6993 [=========================>....] - ETA: 0s - loss: 1.2863 - accuracy: 0.5531 6993/6993 [==============================] - 1s 82us/sample - loss: 1.2740 - accuracy: 0.5586 - val_loss: 0.9349 - val_accuracy: 0.6835 Epoch 3/199 128/6993 [..............................] - ETA: 0s - loss: 1.1283 - accuracy: 0.6250 896/6993 [==>...........................] - ETA: 0s - loss: 1.0266 - accuracy: 0.6507 1792/6993 [======>.......................] - ETA: 0s - loss: 1.0522 - accuracy: 0.6468 2560/6993 [=========>....................] - ETA: 0s - loss: 1.0743 - accuracy: 0.6324 3328/6993 [=============>................] - ETA: 0s - loss: 1.0723 - accuracy: 0.6319 3968/6993 [================>.............] - ETA: 0s - loss: 1.0786 - accuracy: 0.6280 4736/6993 [===================>..........] - ETA: 0s - loss: 1.0660 - accuracy: 0.6334 5376/6993 [======================>.......] - ETA: 0s - loss: 1.0628 - accuracy: 0.6375 6144/6993 [=========================>....] - ETA: 0s - loss: 1.0497 - accuracy: 0.6437 6912/6993 [============================>.] - ETA: 0s - loss: 1.0438 - accuracy: 0.6466 6993/6993 [==============================] - 1s 81us/sample - loss: 1.0424 - accuracy: 0.6474 - val_loss: 0.8002 - val_accuracy: 0.7290 Epoch 4/199 128/6993 [..............................] - ETA: 0s - loss: 0.9389 - accuracy: 0.6719
2022-04-11 23:27:56.862923: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll 2022-04-11 23:27:59.430324: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 2022-04-11 23:27:59.435400: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll 2022-04-11 23:27:59.758269: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:27:59.758303: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:27:59.765936: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:28:00.545209: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:28:00.545233: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:28:00.545246: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:28:00.558682: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) WARNING:tensorflow:From D:\Programs\Anaconda_app\envs\comp47650_env\lib\site-packages\tensorflow_core\python\ops\resource_variable_ops.py:1630: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version. Instructions for updating: If using Keras pass *_constraint arguments to layers. 2022-04-11 23:28:00.661558: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:28:00.661588: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:28:00.668022: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:28:02.474513: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll 2022-04-11 23:29:56.229150: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:29:56.229176: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:29:56.234989: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:29:56.235061: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:29:56.235071: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:29:56.235077: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:29:56.241203: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1)
1024/6993 [===>..........................] - ETA: 0s - loss: 0.9528 - accuracy: 0.6758 1792/6993 [======>.......................] - ETA: 0s - loss: 0.9577 - accuracy: 0.6836 2688/6993 [==========>...................] - ETA: 0s - loss: 0.9489 - accuracy: 0.6920 3584/6993 [==============>...............] - ETA: 0s - loss: 0.9389 - accuracy: 0.6939 4480/6993 [==================>...........] - ETA: 0s - loss: 0.9257 - accuracy: 0.6971 5376/6993 [======================>.......] - ETA: 0s - loss: 0.9239 - accuracy: 0.6981 6272/6993 [=========================>....] - ETA: 0s - loss: 0.9184 - accuracy: 0.6985 6993/6993 [==============================] - 1s 76us/sample - loss: 0.9200 - accuracy: 0.6983 - val_loss: 0.7341 - val_accuracy: 0.7503 Epoch 5/199 128/6993 [..............................] - ETA: 0s - loss: 0.6234 - accuracy: 0.8516 896/6993 [==>...........................] - ETA: 0s - loss: 0.7994 - accuracy: 0.7455 1792/6993 [======>.......................] - ETA: 0s - loss: 0.8027 - accuracy: 0.7444 2688/6993 [==========>...................] - ETA: 0s - loss: 0.8017 - accuracy: 0.7493 3456/6993 [=============>................] - ETA: 0s - loss: 0.8013 - accuracy: 0.7465 4224/6993 [=================>............] - ETA: 0s - loss: 0.7980 - accuracy: 0.7472 5120/6993 [====================>.........] - ETA: 0s - loss: 0.7987 - accuracy: 0.7475 6016/6993 [========================>.....] - ETA: 0s - loss: 0.7980 - accuracy: 0.7453 6912/6993 [============================>.] - ETA: 0s - loss: 0.8012 - accuracy: 0.7441 6993/6993 [==============================] - 1s 74us/sample - loss: 0.8034 - accuracy: 0.7439 - val_loss: 0.7601 - val_accuracy: 0.7700 Epoch 6/199 128/6993 [..............................] - ETA: 0s - loss: 0.8439 - accuracy: 0.7266 896/6993 [==>...........................] - ETA: 0s - loss: 0.7389 - accuracy: 0.7444 1664/6993 [======>.......................] - ETA: 0s - loss: 0.7370 - accuracy: 0.7578 2432/6993 [=========>....................] - ETA: 0s - loss: 0.7331 - accuracy: 0.7623 3072/6993 [============>.................] - ETA: 0s - loss: 0.7368 - accuracy: 0.7620 3840/6993 [===============>..............] - ETA: 0s - loss: 0.7319 - accuracy: 0.7654 4608/6993 [==================>...........] - ETA: 0s - loss: 0.7274 - accuracy: 0.7654 5376/6993 [======================>.......] - ETA: 0s - loss: 0.7184 - accuracy: 0.7690 6144/6993 [=========================>....] - ETA: 0s - loss: 0.7188 - accuracy: 0.7702 6993/6993 [==============================] - 1s 78us/sample - loss: 0.7119 - accuracy: 0.7726 - val_loss: 0.6539 - val_accuracy: 0.7973 Epoch 7/199 128/6993 [..............................] - ETA: 0s - loss: 0.7015 - accuracy: 0.7891 1024/6993 [===>..........................] - ETA: 0s - loss: 0.6582 - accuracy: 0.8018 2048/6993 [=======>......................] - ETA: 0s - loss: 0.6680 - accuracy: 0.7886 2944/6993 [===========>..................] - ETA: 0s - loss: 0.6730 - accuracy: 0.7853 3840/6993 [===============>..............] - ETA: 0s - loss: 0.6578 - accuracy: 0.7885 4736/6993 [===================>..........] - ETA: 0s - loss: 0.6464 - accuracy: 0.7920 5632/6993 [=======================>......] - ETA: 0s - loss: 0.6482 - accuracy: 0.7910 6528/6993 [===========================>..] - ETA: 0s - loss: 0.6446 - accuracy: 0.7901 6993/6993 [==============================] - 1s 74us/sample - loss: 0.6465 - accuracy: 0.7894 - val_loss: 0.6115 - val_accuracy: 0.8043 Epoch 8/199 128/6993 [..............................] - ETA: 0s - loss: 0.6140 - accuracy: 0.7891 896/6993 [==>...........................] - ETA: 0s - loss: 0.5606 - accuracy: 0.8248 1792/6993 [======>.......................] - ETA: 0s - loss: 0.5570 - accuracy: 0.8253 2688/6993 [==========>...................] - ETA: 0s - loss: 0.5584 - accuracy: 0.8292 3584/6993 [==============>...............] - ETA: 0s - loss: 0.5587 - accuracy: 0.8273 4480/6993 [==================>...........] - ETA: 0s - loss: 0.5654 - accuracy: 0.8239 5248/6993 [=====================>........] - ETA: 0s - loss: 0.5655 - accuracy: 0.8215 6144/6993 [=========================>....] - ETA: 0s - loss: 0.5702 - accuracy: 0.8201 6912/6993 [============================>.] - ETA: 0s - loss: 0.5771 - accuracy: 0.8181 6993/6993 [==============================] - 1s 78us/sample - loss: 0.5764 - accuracy: 0.8184 - val_loss: 0.5277 - val_accuracy: 0.8311 Epoch 9/199 128/6993 [..............................] - ETA: 0s - loss: 0.4148 - accuracy: 0.8438 1024/6993 [===>..........................] - ETA: 0s - loss: 0.4669 - accuracy: 0.8467 1664/6993 [======>.......................] - ETA: 0s - loss: 0.5114 - accuracy: 0.8365 2304/6993 [========>.....................] - ETA: 0s - loss: 0.5006 - accuracy: 0.8416 2944/6993 [===========>..................] - ETA: 0s - loss: 0.4980 - accuracy: 0.8414 3584/6993 [==============>...............] - ETA: 0s - loss: 0.5122 - accuracy: 0.8354
2022-04-11 23:29:57.169098: W tensorflow/python/util/util.cc:299] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them. 2022-04-11 23:29:58.590722: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:29:58.590747: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:29:58.596568: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:29:58.596641: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:29:58.596651: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:29:58.596657: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:29:58.602503: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) 2022-04-11 23:31:59.644513: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:31:59.644539: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:31:59.651522: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:31:59.651630: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:31:59.651648: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:31:59.651658: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:31:59.659803: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) 2022-04-11 23:34:23.903160: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:34:23.903191: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:34:23.911630: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:34:23.911722: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:34:23.911734: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:34:23.911741: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:34:23.920287: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) 2022-04-11 23:36:56.785085: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.6705 pciBusID: 0000:01:00.0 2022-04-11 23:36:56.785125: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check. 2022-04-11 23:36:56.794719: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0 2022-04-11 23:36:56.795003: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-04-11 23:36:56.795035: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 2022-04-11 23:36:56.795050: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N 2022-04-11 23:36:56.805696: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4846 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1)
4224/6993 [=================>............] - ETA: 0s - loss: 0.5245 - accuracy: 0.8321 4992/6993 [====================>.........] - ETA: 0s - loss: 0.5263 - accuracy: 0.8309 5632/6993 [=======================>......] - ETA: 0s - loss: 0.5249 - accuracy: 0.8320 6272/6993 [=========================>....] - ETA: 0s - loss: 0.5274 - accuracy: 0.8316 6912/6993 [============================>.] - ETA: 0s - loss: 0.5287 - accuracy: 0.8320 6993/6993 [==============================] - 1s 88us/sample - loss: 0.5275 - accuracy: 0.8323 - val_loss: 0.5061 - val_accuracy: 0.8311 Epoch 10/199 128/6993 [..............................] - ETA: 0s - loss: 0.5958 - accuracy: 0.8359 768/6993 [==>...........................] - ETA: 0s - loss: 0.4798 - accuracy: 0.8490 1408/6993 [=====>........................] - ETA: 0s - loss: 0.4696 - accuracy: 0.8551 2048/6993 [=======>......................] - ETA: 0s - loss: 0.4724 - accuracy: 0.8560 2688/6993 [==========>...................] - ETA: 0s - loss: 0.4787 - accuracy: 0.8508 3456/6993 [=============>................] - ETA: 0s - loss: 0.4845 - accuracy: 0.8507 4352/6993 [=================>............] - ETA: 0s - loss: 0.4938 - accuracy: 0.8497 5120/6993 [====================>.........] - ETA: 0s - loss: 0.4932 - accuracy: 0.8453 5888/6993 [========================>.....] - ETA: 0s - loss: 0.4851 - accuracy: 0.8475 6784/6993 [============================>.] - ETA: 0s - loss: 0.4849 - accuracy: 0.8486 6993/6993 [==============================] - 1s 88us/sample - loss: 0.4807 - accuracy: 0.8497 - val_loss: 0.5132 - val_accuracy: 0.8392 Epoch 11/199 128/6993 [..............................] - ETA: 0s - loss: 0.3582 - accuracy: 0.8984 1024/6993 [===>..........................] - ETA: 0s - loss: 0.3717 - accuracy: 0.8740 2048/6993 [=======>......................] - ETA: 0s - loss: 0.3935 - accuracy: 0.8682 2816/6993 [===========>..................] - ETA: 0s - loss: 0.4297 - accuracy: 0.8601 3584/6993 [==============>...............] - ETA: 0s - loss: 0.4282 - accuracy: 0.8658 4352/6993 [=================>............] - ETA: 0s - loss: 0.4303 - accuracy: 0.8674 5120/6993 [====================>.........] - ETA: 0s - loss: 0.4323 - accuracy: 0.8670 5888/6993 [========================>.....] - ETA: 0s - loss: 0.4372 - accuracy: 0.8662 6656/6993 [===========================>..] - ETA: 0s - loss: 0.4367 - accuracy: 0.8646 6993/6993 [==============================] - 1s 79us/sample - loss: 0.4407 - accuracy: 0.8631 - val_loss: 0.5021 - val_accuracy: 0.8524 Epoch 12/199 128/6993 [..............................] - ETA: 0s - loss: 0.3598 - accuracy: 0.8594 896/6993 [==>...........................] - ETA: 0s - loss: 0.4105 - accuracy: 0.8717 1664/6993 [======>.......................] - ETA: 0s - loss: 0.3975 - accuracy: 0.8726 2432/6993 [=========>....................] - ETA: 0s - loss: 0.4088 - accuracy: 0.8717 3072/6993 [============>.................] - ETA: 0s - loss: 0.4026 - accuracy: 0.8730 3712/6993 [==============>...............] - ETA: 0s - loss: 0.3921 - accuracy: 0.8758 4352/6993 [=================>............] - ETA: 0s - loss: 0.3973 - accuracy: 0.8745 4992/6993 [====================>.........] - ETA: 0s - loss: 0.3928 - accuracy: 0.8756 5632/6993 [=======================>......] - ETA: 0s - loss: 0.3925 - accuracy: 0.8752 6400/6993 [==========================>...] - ETA: 0s - loss: 0.4045 - accuracy: 0.8709 6993/6993 [==============================] - 1s 84us/sample - loss: 0.4025 - accuracy: 0.8719 - val_loss: 0.4768 - val_accuracy: 0.8529 Epoch 13/199 128/6993 [..............................] - ETA: 0s - loss: 0.4498 - accuracy: 0.8672 896/6993 [==>...........................] - ETA: 0s - loss: 0.3802 - accuracy: 0.8917 1536/6993 [=====>........................] - ETA: 0s - loss: 0.3682 - accuracy: 0.8919 2304/6993 [========>.....................] - ETA: 0s - loss: 0.3616 - accuracy: 0.8950 3072/6993 [============>.................] - ETA: 0s - loss: 0.3712 - accuracy: 0.8903 3840/6993 [===============>..............] - ETA: 0s - loss: 0.3708 - accuracy: 0.8906 4608/6993 [==================>...........] - ETA: 0s - loss: 0.3714 - accuracy: 0.8891 5504/6993 [======================>.......] - ETA: 0s - loss: 0.3783 - accuracy: 0.8861 6400/6993 [==========================>...] - ETA: 0s - loss: 0.3773 - accuracy: 0.8833 6993/6993 [==============================] - 1s 80us/sample - loss: 0.3728 - accuracy: 0.8862 - val_loss: 0.4073 - val_accuracy: 0.8731 Epoch 14/199 128/6993 [..............................] - ETA: 0s - loss: 0.2758 - accuracy: 0.9141 896/6993 [==>...........................] - ETA: 0s - loss: 0.3073 - accuracy: 0.9018 1536/6993 [=====>........................] - ETA: 0s - loss: 0.3336 - accuracy: 0.8984 2304/6993 [========>.....................] - ETA: 0s - loss: 0.3265 - accuracy: 0.8984 2944/6993 [===========>..................] - ETA: 0s - loss: 0.3411 - accuracy: 0.8947 3584/6993 [==============>...............] - ETA: 0s - loss: 0.3412 - accuracy: 0.8945 4224/6993 [=================>............] - ETA: 0s - loss: 0.3452 - accuracy: 0.8918 4864/6993 [===================>..........] - ETA: 0s - loss: 0.3470 - accuracy: 0.8917 5504/6993 [======================>.......] - ETA: 0s - loss: 0.3452 - accuracy: 0.8932 6144/6993 [=========================>....] - ETA: 0s - loss: 0.3451 - accuracy: 0.8921 6784/6993 [============================>.] - ETA: 0s - loss: 0.3513 - accuracy: 0.8920 6993/6993 [==============================] - 1s 86us/sample - loss: 0.3488 - accuracy: 0.8922 - val_loss: 0.3937 - val_accuracy: 0.8862 Epoch 15/199 128/6993 [..............................] - ETA: 0s - loss: 0.2672 - accuracy: 0.9531 768/6993 [==>...........................] - ETA: 0s - loss: 0.3210 - accuracy: 0.9102 1408/6993 [=====>........................] - ETA: 0s - loss: 0.3459 - accuracy: 0.8920 2048/6993 [=======>......................] - ETA: 0s - loss: 0.3287 - accuracy: 0.8955 2816/6993 [===========>..................] - ETA: 0s - loss: 0.3286 - accuracy: 0.8967 3584/6993 [==============>...............] - ETA: 0s - loss: 0.3248 - accuracy: 0.9001 4224/6993 [=================>............] - ETA: 0s - loss: 0.3209 - accuracy: 0.8984 4992/6993 [====================>.........] - ETA: 0s - loss: 0.3184 - accuracy: 0.8986 5632/6993 [=======================>......] - ETA: 0s - loss: 0.3199 - accuracy: 0.8979 6400/6993 [==========================>...] - ETA: 0s - loss: 0.3166 - accuracy: 0.8991 6993/6993 [==============================] - 1s 85us/sample - loss: 0.3126 - accuracy: 0.9012 - val_loss: 0.4102 - val_accuracy: 0.8827 Epoch 16/199 128/6993 [..............................] - ETA: 0s - loss: 0.1924 - accuracy: 0.9453 896/6993 [==>...........................] - ETA: 0s - loss: 0.3163 - accuracy: 0.9085 1664/6993 [======>.......................] - ETA: 0s - loss: 0.3113 - accuracy: 0.9117 2432/6993 [=========>....................] - ETA: 0s - loss: 0.3076 - accuracy: 0.9095 3200/6993 [============>.................] - ETA: 0s - loss: 0.3074 - accuracy: 0.9091 3968/6993 [================>.............] - ETA: 0s - loss: 0.3013 - accuracy: 0.9103 4736/6993 [===================>..........] - ETA: 0s - loss: 0.2975 - accuracy: 0.9128 5504/6993 [======================>.......] - ETA: 0s - loss: 0.3048 - accuracy: 0.9117 6528/6993 [===========================>..] - ETA: 0s - loss: 0.3028 - accuracy: 0.9124 6993/6993 [==============================] - 1s 80us/sample - loss: 0.2991 - accuracy: 0.9125 - val_loss: 0.3845 - val_accuracy: 0.8868 Epoch 17/199 128/6993 [..............................] - ETA: 0s - loss: 0.2859 - accuracy: 0.9141 896/6993 [==>...........................] - ETA: 0s - loss: 0.3314 - accuracy: 0.8917 1664/6993 [======>.......................] - ETA: 0s - loss: 0.3133 - accuracy: 0.8996 2432/6993 [=========>....................] - ETA: 0s - loss: 0.2886 - accuracy: 0.9087 3200/6993 [============>.................] - ETA: 0s - loss: 0.2884 - accuracy: 0.9097 3968/6993 [================>.............] - ETA: 0s - loss: 0.2884 - accuracy: 0.9115 4736/6993 [===================>..........] - ETA: 0s - loss: 0.2850 - accuracy: 0.9120 5504/6993 [======================>.......] - ETA: 0s - loss: 0.2864 - accuracy: 0.9124 6272/6993 [=========================>....] - ETA: 0s - loss: 0.2833 - accuracy: 0.9139 6993/6993 [==============================] - 1s 77us/sample - loss: 0.2876 - accuracy: 0.9128 - val_loss: 0.4608 - val_accuracy: 0.8645 Epoch 18/199 128/6993 [..............................] - ETA: 0s - loss: 0.2981 - accuracy: 0.9219 640/6993 [=>............................] - ETA: 0s - loss: 0.2442 - accuracy: 0.9297 1280/6993 [====>.........................] - ETA: 0s - loss: 0.2716 - accuracy: 0.9258 2048/6993 [=======>......................] - ETA: 0s - loss: 0.2569 - accuracy: 0.9268 2816/6993 [===========>..................] - ETA: 0s - loss: 0.2515 - accuracy: 0.9268 3456/6993 [=============>................] - ETA: 0s - loss: 0.2558 - accuracy: 0.9285 4224/6993 [=================>............] - ETA: 0s - loss: 0.2693 - accuracy: 0.9268 4992/6993 [====================>.........] - ETA: 0s - loss: 0.2633 - accuracy: 0.9279 5760/6993 [=======================>......] - ETA: 0s - loss: 0.2694 - accuracy: 0.9253 6528/6993 [===========================>..] - ETA: 0s - loss: 0.2683 - accuracy: 0.9260 6993/6993 [==============================] - 1s 83us/sample - loss: 0.2696 - accuracy: 0.9258 - val_loss: 0.3673 - val_accuracy: 0.8938 Epoch 19/199 128/6993 [..............................] - ETA: 0s - loss: 0.1266 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.2102 - accuracy: 0.9420 1664/6993 [======>.......................] - ETA: 0s - loss: 0.2340 - accuracy: 0.9303 2432/6993 [=========>....................] - ETA: 0s - loss: 0.2457 - accuracy: 0.9276 3200/6993 [============>.................] - ETA: 0s - loss: 0.2502 - accuracy: 0.9266 3968/6993 [================>.............] - ETA: 0s - loss: 0.2563 - accuracy: 0.9277 4736/6993 [===================>..........] - ETA: 0s - loss: 0.2580 - accuracy: 0.9244 5376/6993 [======================>.......] - ETA: 0s - loss: 0.2586 - accuracy: 0.9241 6016/6993 [========================>.....] - ETA: 0s - loss: 0.2600 - accuracy: 0.9232 6784/6993 [============================>.] - ETA: 0s - loss: 0.2556 - accuracy: 0.9233 6993/6993 [==============================] - 1s 89us/sample - loss: 0.2559 - accuracy: 0.9229 - val_loss: 0.4241 - val_accuracy: 0.8873 Epoch 20/199 128/6993 [..............................] - ETA: 0s - loss: 0.2615 - accuracy: 0.9062 768/6993 [==>...........................] - ETA: 0s - loss: 0.2284 - accuracy: 0.9206 1664/6993 [======>.......................] - ETA: 0s - loss: 0.2303 - accuracy: 0.9303 2560/6993 [=========>....................] - ETA: 0s - loss: 0.2241 - accuracy: 0.9344 3456/6993 [=============>................] - ETA: 0s - loss: 0.2377 - accuracy: 0.9308 4352/6993 [=================>............] - ETA: 0s - loss: 0.2362 - accuracy: 0.9322 5248/6993 [=====================>........] - ETA: 0s - loss: 0.2299 - accuracy: 0.9333 6144/6993 [=========================>....] - ETA: 0s - loss: 0.2319 - accuracy: 0.9315 6993/6993 [==============================] - 1s 76us/sample - loss: 0.2334 - accuracy: 0.9306 - val_loss: 0.4584 - val_accuracy: 0.8736 Epoch 21/199 128/6993 [..............................] - ETA: 0s - loss: 0.2472 - accuracy: 0.9219 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2431 - accuracy: 0.9307 1920/6993 [=======>......................] - ETA: 0s - loss: 0.2209 - accuracy: 0.9349 2816/6993 [===========>..................] - ETA: 0s - loss: 0.2281 - accuracy: 0.9343 3712/6993 [==============>...............] - ETA: 0s - loss: 0.2132 - accuracy: 0.9394 4608/6993 [==================>...........] - ETA: 0s - loss: 0.2118 - accuracy: 0.9384 5504/6993 [======================>.......] - ETA: 0s - loss: 0.2100 - accuracy: 0.9377 6400/6993 [==========================>...] - ETA: 0s - loss: 0.2182 - accuracy: 0.9352 6993/6993 [==============================] - 1s 77us/sample - loss: 0.2164 - accuracy: 0.9355 - val_loss: 0.3834 - val_accuracy: 0.8913 Epoch 22/199 128/6993 [..............................] - ETA: 0s - loss: 0.0964 - accuracy: 0.9609 1152/6993 [===>..........................] - ETA: 0s - loss: 0.1751 - accuracy: 0.9436 2048/6993 [=======>......................] - ETA: 0s - loss: 0.2112 - accuracy: 0.9380 2944/6993 [===========>..................] - ETA: 0s - loss: 0.2028 - accuracy: 0.9409 3840/6993 [===============>..............] - ETA: 0s - loss: 0.2021 - accuracy: 0.9406 4736/6993 [===================>..........] - ETA: 0s - loss: 0.2051 - accuracy: 0.9379 5632/6993 [=======================>......] - ETA: 0s - loss: 0.2088 - accuracy: 0.9359 6528/6993 [===========================>..] - ETA: 0s - loss: 0.2108 - accuracy: 0.9363 6993/6993 [==============================] - 1s 74us/sample - loss: 0.2110 - accuracy: 0.9355 - val_loss: 0.4289 - val_accuracy: 0.8857 Epoch 23/199 128/6993 [..............................] - ETA: 0s - loss: 0.2333 - accuracy: 0.9219 768/6993 [==>...........................] - ETA: 0s - loss: 0.1692 - accuracy: 0.9492 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1681 - accuracy: 0.9489 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1857 - accuracy: 0.9448 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1992 - accuracy: 0.9428 3712/6993 [==============>...............] - ETA: 0s - loss: 0.2038 - accuracy: 0.9410 4352/6993 [=================>............] - ETA: 0s - loss: 0.1970 - accuracy: 0.9419 4992/6993 [====================>.........] - ETA: 0s - loss: 0.2051 - accuracy: 0.9389 5760/6993 [=======================>......] - ETA: 0s - loss: 0.2026 - accuracy: 0.9396 6528/6993 [===========================>..] - ETA: 0s - loss: 0.2077 - accuracy: 0.9393 6993/6993 [==============================] - 1s 83us/sample - loss: 0.2044 - accuracy: 0.9402 - val_loss: 0.3493 - val_accuracy: 0.9039 Epoch 24/199 128/6993 [..............................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1494 - accuracy: 0.9520 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1608 - accuracy: 0.9492 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1701 - accuracy: 0.9488 3072/6993 [============>.................] - ETA: 0s - loss: 0.1701 - accuracy: 0.9492 3968/6993 [================>.............] - ETA: 0s - loss: 0.1838 - accuracy: 0.9453 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1879 - accuracy: 0.9449 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1863 - accuracy: 0.9455 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1852 - accuracy: 0.9453 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1877 - accuracy: 0.9455 - val_loss: 0.3698 - val_accuracy: 0.8974 Epoch 25/199 128/6993 [..............................] - ETA: 0s - loss: 0.2837 - accuracy: 0.9141 896/6993 [==>...........................] - ETA: 0s - loss: 0.2362 - accuracy: 0.9252 1664/6993 [======>.......................] - ETA: 0s - loss: 0.2005 - accuracy: 0.9405 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1872 - accuracy: 0.9457 3200/6993 [============>.................] - ETA: 0s - loss: 0.1841 - accuracy: 0.9463 3968/6993 [================>.............] - ETA: 0s - loss: 0.1841 - accuracy: 0.9471 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1896 - accuracy: 0.9468 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1829 - accuracy: 0.9483 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1863 - accuracy: 0.9467 6993/6993 [==============================] - 1s 79us/sample - loss: 0.1869 - accuracy: 0.9467 - val_loss: 0.3690 - val_accuracy: 0.9024 Epoch 26/199 128/6993 [..............................] - ETA: 0s - loss: 0.2920 - accuracy: 0.9219 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2003 - accuracy: 0.9443 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1895 - accuracy: 0.9453 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1889 - accuracy: 0.9453 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1947 - accuracy: 0.9453 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1878 - accuracy: 0.9477 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1859 - accuracy: 0.9485 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1870 - accuracy: 0.9494 6912/6993 [============================>.] - ETA: 0s - loss: 0.1875 - accuracy: 0.9498 6993/6993 [==============================] - 1s 79us/sample - loss: 0.1878 - accuracy: 0.9494 - val_loss: 0.4255 - val_accuracy: 0.8969 Epoch 27/199 128/6993 [..............................] - ETA: 0s - loss: 0.1930 - accuracy: 0.9531 768/6993 [==>...........................] - ETA: 0s - loss: 0.1793 - accuracy: 0.9518 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1811 - accuracy: 0.9517 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1730 - accuracy: 0.9536 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1618 - accuracy: 0.9535 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1627 - accuracy: 0.9504 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1624 - accuracy: 0.9501 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1541 - accuracy: 0.9522 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1522 - accuracy: 0.9526 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1595 - accuracy: 0.9505 - val_loss: 0.3705 - val_accuracy: 0.9105 Epoch 28/199 128/6993 [..............................] - ETA: 0s - loss: 0.1234 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1179 - accuracy: 0.9658 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1323 - accuracy: 0.9615 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1481 - accuracy: 0.9574 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1580 - accuracy: 0.9550 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1670 - accuracy: 0.9525 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1621 - accuracy: 0.9531 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1666 - accuracy: 0.9509 6912/6993 [============================>.] - ETA: 0s - loss: 0.1627 - accuracy: 0.9524 6993/6993 [==============================] - 1s 79us/sample - loss: 0.1623 - accuracy: 0.9524 - val_loss: 0.3599 - val_accuracy: 0.9075 Epoch 29/199 128/6993 [..............................] - ETA: 0s - loss: 0.1530 - accuracy: 0.9531 768/6993 [==>...........................] - ETA: 0s - loss: 0.1395 - accuracy: 0.9596 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1461 - accuracy: 0.9551 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1424 - accuracy: 0.9566 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1426 - accuracy: 0.9572 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1488 - accuracy: 0.9558 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1577 - accuracy: 0.9533 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1620 - accuracy: 0.9531 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1597 - accuracy: 0.9526 6784/6993 [============================>.] - ETA: 0s - loss: 0.1569 - accuracy: 0.9539 6993/6993 [==============================] - 1s 87us/sample - loss: 0.1566 - accuracy: 0.9541 - val_loss: 0.3934 - val_accuracy: 0.9095 Epoch 30/199 128/6993 [..............................] - ETA: 0s - loss: 0.2417 - accuracy: 0.9453 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1417 - accuracy: 0.9668 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1569 - accuracy: 0.9609 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1680 - accuracy: 0.9581 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1526 - accuracy: 0.9596 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1528 - accuracy: 0.9588 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1533 - accuracy: 0.9589 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1601 - accuracy: 0.9565 6993/6993 [==============================] - 1s 76us/sample - loss: 0.1604 - accuracy: 0.9570 - val_loss: 0.4199 - val_accuracy: 0.9014 Epoch 31/199 128/6993 [..............................] - ETA: 0s - loss: 0.0947 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1607 - accuracy: 0.9619 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1591 - accuracy: 0.9547 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1454 - accuracy: 0.9577 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1528 - accuracy: 0.9558 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1547 - accuracy: 0.9554 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1535 - accuracy: 0.9567 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1529 - accuracy: 0.9579 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1547 - accuracy: 0.9577 - val_loss: 0.3995 - val_accuracy: 0.9019 Epoch 32/199 128/6993 [..............................] - ETA: 0s - loss: 0.1568 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.1321 - accuracy: 0.9643 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1440 - accuracy: 0.9598 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1245 - accuracy: 0.9633 3456/6993 [=============>................] - ETA: 0s - loss: 0.1228 - accuracy: 0.9624 4352/6993 [=================>............] - ETA: 0s - loss: 0.1355 - accuracy: 0.9602 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1336 - accuracy: 0.9598 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1414 - accuracy: 0.9581 6912/6993 [============================>.] - ETA: 0s - loss: 0.1426 - accuracy: 0.9591 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1433 - accuracy: 0.9587 - val_loss: 0.4017 - val_accuracy: 0.9110 Epoch 33/199 128/6993 [..............................] - ETA: 0s - loss: 0.1645 - accuracy: 0.9453 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1267 - accuracy: 0.9619 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1291 - accuracy: 0.9643 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1354 - accuracy: 0.9628 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1338 - accuracy: 0.9615 4224/6993 [=================>............] - ETA: 0s - loss: 0.1392 - accuracy: 0.9595 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1379 - accuracy: 0.9586 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1425 - accuracy: 0.9574 6784/6993 [============================>.] - ETA: 0s - loss: 0.1359 - accuracy: 0.9596 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1362 - accuracy: 0.9595 - val_loss: 0.4297 - val_accuracy: 0.9060 Epoch 34/199 128/6993 [..............................] - ETA: 0s - loss: 0.3287 - accuracy: 0.9062 896/6993 [==>...........................] - ETA: 0s - loss: 0.1934 - accuracy: 0.9475 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1517 - accuracy: 0.9559 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1318 - accuracy: 0.9598 3456/6993 [=============>................] - ETA: 0s - loss: 0.1445 - accuracy: 0.9580 4224/6993 [=================>............] - ETA: 0s - loss: 0.1451 - accuracy: 0.9571 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1416 - accuracy: 0.9587 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1380 - accuracy: 0.9578 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1334 - accuracy: 0.9591 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1354 - accuracy: 0.9597 - val_loss: 0.3745 - val_accuracy: 0.9105 Epoch 35/199 128/6993 [..............................] - ETA: 0s - loss: 0.2678 - accuracy: 0.9375 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1426 - accuracy: 0.9658 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1333 - accuracy: 0.9648 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1261 - accuracy: 0.9658 3328/6993 [=============>................] - ETA: 0s - loss: 0.1311 - accuracy: 0.9648 4096/6993 [================>.............] - ETA: 0s - loss: 0.1238 - accuracy: 0.9661 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1243 - accuracy: 0.9647 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1266 - accuracy: 0.9645 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1309 - accuracy: 0.9648 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1323 - accuracy: 0.9645 - val_loss: 0.4167 - val_accuracy: 0.9100 Epoch 36/199 128/6993 [..............................] - ETA: 0s - loss: 0.1420 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1247 - accuracy: 0.9621 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1248 - accuracy: 0.9627 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1409 - accuracy: 0.9605 3200/6993 [============>.................] - ETA: 0s - loss: 0.1431 - accuracy: 0.9591 3968/6993 [================>.............] - ETA: 0s - loss: 0.1327 - accuracy: 0.9630 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1230 - accuracy: 0.9650 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1248 - accuracy: 0.9648 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1224 - accuracy: 0.9655 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1254 - accuracy: 0.9653 - val_loss: 0.4313 - val_accuracy: 0.9039 Epoch 37/199 128/6993 [..............................] - ETA: 0s - loss: 0.0923 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1065 - accuracy: 0.9654 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1157 - accuracy: 0.9639 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1200 - accuracy: 0.9655 3200/6993 [============>.................] - ETA: 0s - loss: 0.1179 - accuracy: 0.9656 4096/6993 [================>.............] - ETA: 0s - loss: 0.1210 - accuracy: 0.9646 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1211 - accuracy: 0.9655 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1206 - accuracy: 0.9655 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1182 - accuracy: 0.9665 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1167 - accuracy: 0.9667 - val_loss: 0.4515 - val_accuracy: 0.9100 Epoch 38/199 128/6993 [..............................] - ETA: 0s - loss: 0.0454 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1440 - accuracy: 0.9643 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1325 - accuracy: 0.9654 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1353 - accuracy: 0.9642 3328/6993 [=============>................] - ETA: 0s - loss: 0.1461 - accuracy: 0.9630 3968/6993 [================>.............] - ETA: 0s - loss: 0.1422 - accuracy: 0.9635 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1359 - accuracy: 0.9652 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1315 - accuracy: 0.9651 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1326 - accuracy: 0.9650 6912/6993 [============================>.] - ETA: 0s - loss: 0.1357 - accuracy: 0.9638 6993/6993 [==============================] - 1s 90us/sample - loss: 0.1352 - accuracy: 0.9640 - val_loss: 0.4365 - val_accuracy: 0.9100 Epoch 39/199 128/6993 [..............................] - ETA: 0s - loss: 0.0676 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0592 - accuracy: 0.9818 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0716 - accuracy: 0.9785 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1115 - accuracy: 0.9720 3200/6993 [============>.................] - ETA: 0s - loss: 0.1210 - accuracy: 0.9697 4096/6993 [================>.............] - ETA: 0s - loss: 0.1195 - accuracy: 0.9685 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1199 - accuracy: 0.9681 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1174 - accuracy: 0.9688 6784/6993 [============================>.] - ETA: 0s - loss: 0.1180 - accuracy: 0.9683 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1198 - accuracy: 0.9677 - val_loss: 0.4231 - val_accuracy: 0.9085 Epoch 40/199 128/6993 [..............................] - ETA: 0s - loss: 0.0924 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.1023 - accuracy: 0.9766 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1069 - accuracy: 0.9754 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1150 - accuracy: 0.9715 3456/6993 [=============>................] - ETA: 0s - loss: 0.1088 - accuracy: 0.9722 4224/6993 [=================>............] - ETA: 0s - loss: 0.1069 - accuracy: 0.9711 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1108 - accuracy: 0.9699 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1147 - accuracy: 0.9692 6912/6993 [============================>.] - ETA: 0s - loss: 0.1120 - accuracy: 0.9692 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1112 - accuracy: 0.9694 - val_loss: 0.4503 - val_accuracy: 0.9176 Epoch 41/199 128/6993 [..............................] - ETA: 0s - loss: 0.1647 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.1077 - accuracy: 0.9766 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0866 - accuracy: 0.9784 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0902 - accuracy: 0.9738 3456/6993 [=============>................] - ETA: 0s - loss: 0.0987 - accuracy: 0.9731 4224/6993 [=================>............] - ETA: 0s - loss: 0.0947 - accuracy: 0.9740 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1017 - accuracy: 0.9727 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1023 - accuracy: 0.9724 6912/6993 [============================>.] - ETA: 0s - loss: 0.1052 - accuracy: 0.9714 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1049 - accuracy: 0.9714 - val_loss: 0.4237 - val_accuracy: 0.9156 Epoch 42/199 128/6993 [..............................] - ETA: 0s - loss: 0.1506 - accuracy: 0.9609 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1054 - accuracy: 0.9697 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1149 - accuracy: 0.9682 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1342 - accuracy: 0.9638 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1405 - accuracy: 0.9601 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1387 - accuracy: 0.9609 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1275 - accuracy: 0.9628 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1208 - accuracy: 0.9651 6993/6993 [==============================] - 1s 79us/sample - loss: 0.1193 - accuracy: 0.9660 - val_loss: 0.3922 - val_accuracy: 0.9196 Epoch 43/199 128/6993 [..............................] - ETA: 0s - loss: 0.0292 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0858 - accuracy: 0.9775 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0839 - accuracy: 0.9792 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0876 - accuracy: 0.9769 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0976 - accuracy: 0.9755 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1129 - accuracy: 0.9718 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1135 - accuracy: 0.9700 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1113 - accuracy: 0.9706 6993/6993 [==============================] - 1s 77us/sample - loss: 0.1129 - accuracy: 0.9705 - val_loss: 0.4426 - val_accuracy: 0.9060 Epoch 44/199 128/6993 [..............................] - ETA: 0s - loss: 0.1791 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.1038 - accuracy: 0.9721 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1006 - accuracy: 0.9721 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1043 - accuracy: 0.9710 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0983 - accuracy: 0.9715 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1061 - accuracy: 0.9703 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1103 - accuracy: 0.9697 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1081 - accuracy: 0.9695 6993/6993 [==============================] - 1s 77us/sample - loss: 0.1069 - accuracy: 0.9704 - val_loss: 0.4430 - val_accuracy: 0.9151 Epoch 45/199 128/6993 [..............................] - ETA: 0s - loss: 0.0643 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0808 - accuracy: 0.9824 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0850 - accuracy: 0.9818 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0875 - accuracy: 0.9794 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0848 - accuracy: 0.9790 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0941 - accuracy: 0.9766 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0950 - accuracy: 0.9771 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0984 - accuracy: 0.9758 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0991 - accuracy: 0.9757 - val_loss: 0.4249 - val_accuracy: 0.9171 Epoch 46/199 128/6993 [..............................] - ETA: 0s - loss: 0.0602 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0688 - accuracy: 0.9777 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0845 - accuracy: 0.9760 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0830 - accuracy: 0.9769 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0960 - accuracy: 0.9735 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1026 - accuracy: 0.9712 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1087 - accuracy: 0.9689 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1074 - accuracy: 0.9686 6912/6993 [============================>.] - ETA: 0s - loss: 0.1054 - accuracy: 0.9692 6993/6993 [==============================] - 1s 76us/sample - loss: 0.1060 - accuracy: 0.9690 - val_loss: 0.4122 - val_accuracy: 0.9110 Epoch 47/199 128/6993 [..............................] - ETA: 0s - loss: 0.0724 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1316 - accuracy: 0.9736 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0987 - accuracy: 0.9771 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0900 - accuracy: 0.9769 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0832 - accuracy: 0.9771 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0935 - accuracy: 0.9757 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1004 - accuracy: 0.9741 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0961 - accuracy: 0.9746 6912/6993 [============================>.] - ETA: 0s - loss: 0.0952 - accuracy: 0.9750 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0945 - accuracy: 0.9751 - val_loss: 0.3752 - val_accuracy: 0.9191 Epoch 48/199 128/6993 [..............................] - ETA: 0s - loss: 0.0585 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0840 - accuracy: 0.9746 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0749 - accuracy: 0.9777 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0786 - accuracy: 0.9762 3200/6993 [============>.................] - ETA: 0s - loss: 0.0830 - accuracy: 0.9762 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0858 - accuracy: 0.9766 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0890 - accuracy: 0.9757 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0928 - accuracy: 0.9748 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0933 - accuracy: 0.9736 6784/6993 [============================>.] - ETA: 0s - loss: 0.0966 - accuracy: 0.9729 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0955 - accuracy: 0.9733 - val_loss: 0.4625 - val_accuracy: 0.9166 Epoch 49/199 128/6993 [..............................] - ETA: 0s - loss: 0.0172 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.1297 - accuracy: 0.9743 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1261 - accuracy: 0.9724 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1256 - accuracy: 0.9711 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1180 - accuracy: 0.9721 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1217 - accuracy: 0.9710 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1207 - accuracy: 0.9719 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1164 - accuracy: 0.9722 6912/6993 [============================>.] - ETA: 0s - loss: 0.1144 - accuracy: 0.9724 6993/6993 [==============================] - 1s 76us/sample - loss: 0.1138 - accuracy: 0.9724 - val_loss: 0.4085 - val_accuracy: 0.9216 Epoch 50/199 128/6993 [..............................] - ETA: 0s - loss: 0.1398 - accuracy: 0.9375 896/6993 [==>...........................] - ETA: 0s - loss: 0.0749 - accuracy: 0.9777 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0647 - accuracy: 0.9799 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0700 - accuracy: 0.9799 3456/6993 [=============>................] - ETA: 0s - loss: 0.0944 - accuracy: 0.9786 4352/6993 [=================>............] - ETA: 0s - loss: 0.0908 - accuracy: 0.9789 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0917 - accuracy: 0.9777 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0944 - accuracy: 0.9767 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0946 - accuracy: 0.9770 6912/6993 [============================>.] - ETA: 0s - loss: 0.0970 - accuracy: 0.9766 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0968 - accuracy: 0.9765 - val_loss: 0.4350 - val_accuracy: 0.9146 Epoch 51/199 128/6993 [..............................] - ETA: 0s - loss: 0.0351 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0817 - accuracy: 0.9754 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0900 - accuracy: 0.9706 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0958 - accuracy: 0.9700 3328/6993 [=============>................] - ETA: 0s - loss: 0.0911 - accuracy: 0.9721 3968/6993 [================>.............] - ETA: 0s - loss: 0.0873 - accuracy: 0.9735 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0818 - accuracy: 0.9753 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0885 - accuracy: 0.9731 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0899 - accuracy: 0.9737 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0869 - accuracy: 0.9747 - val_loss: 0.4322 - val_accuracy: 0.9166 Epoch 52/199 128/6993 [..............................] - ETA: 0s - loss: 0.0802 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0739 - accuracy: 0.9766 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0656 - accuracy: 0.9807 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0800 - accuracy: 0.9769 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0875 - accuracy: 0.9760 4352/6993 [=================>............] - ETA: 0s - loss: 0.0892 - accuracy: 0.9761 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0928 - accuracy: 0.9750 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0935 - accuracy: 0.9756 6784/6993 [============================>.] - ETA: 0s - loss: 0.0944 - accuracy: 0.9752 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0938 - accuracy: 0.9750 - val_loss: 0.4490 - val_accuracy: 0.9146 Epoch 53/199 128/6993 [..............................] - ETA: 0s - loss: 0.0202 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0519 - accuracy: 0.9855 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0468 - accuracy: 0.9880 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0657 - accuracy: 0.9828 3456/6993 [=============>................] - ETA: 0s - loss: 0.0706 - accuracy: 0.9806 4352/6993 [=================>............] - ETA: 0s - loss: 0.0739 - accuracy: 0.9795 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0773 - accuracy: 0.9788 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0781 - accuracy: 0.9790 6993/6993 [==============================] - 1s 75us/sample - loss: 0.0804 - accuracy: 0.9785 - val_loss: 0.4679 - val_accuracy: 0.9206 Epoch 54/199 128/6993 [..............................] - ETA: 0s - loss: 0.0779 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0513 - accuracy: 0.9795 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0521 - accuracy: 0.9812 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0837 - accuracy: 0.9780 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1004 - accuracy: 0.9763 4352/6993 [=================>............] - ETA: 0s - loss: 0.0957 - accuracy: 0.9766 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1011 - accuracy: 0.9747 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1050 - accuracy: 0.9746 6993/6993 [==============================] - 1s 76us/sample - loss: 0.1051 - accuracy: 0.9745 - val_loss: 0.4273 - val_accuracy: 0.9181 Epoch 55/199 128/6993 [..............................] - ETA: 0s - loss: 0.1617 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0744 - accuracy: 0.9766 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0689 - accuracy: 0.9781 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0650 - accuracy: 0.9787 3456/6993 [=============>................] - ETA: 0s - loss: 0.0653 - accuracy: 0.9789 4352/6993 [=================>............] - ETA: 0s - loss: 0.0691 - accuracy: 0.9784 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0719 - accuracy: 0.9779 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0734 - accuracy: 0.9782 6912/6993 [============================>.] - ETA: 0s - loss: 0.0794 - accuracy: 0.9773 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0787 - accuracy: 0.9775 - val_loss: 0.4301 - val_accuracy: 0.9247 Epoch 56/199 128/6993 [..............................] - ETA: 0s - loss: 0.0231 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0653 - accuracy: 0.9821 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0917 - accuracy: 0.9760 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0903 - accuracy: 0.9766 3328/6993 [=============>................] - ETA: 0s - loss: 0.0868 - accuracy: 0.9766 4096/6993 [================>.............] - ETA: 0s - loss: 0.0816 - accuracy: 0.9773 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0819 - accuracy: 0.9766 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0830 - accuracy: 0.9784 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0788 - accuracy: 0.9786 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0840 - accuracy: 0.9773 - val_loss: 0.4458 - val_accuracy: 0.9100 Epoch 57/199 128/6993 [..............................] - ETA: 0s - loss: 0.0760 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0955 - accuracy: 0.9707 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1053 - accuracy: 0.9745 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0920 - accuracy: 0.9762 3456/6993 [=============>................] - ETA: 0s - loss: 0.1007 - accuracy: 0.9757 4352/6993 [=================>............] - ETA: 0s - loss: 0.0963 - accuracy: 0.9768 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1060 - accuracy: 0.9748 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0995 - accuracy: 0.9764 6784/6993 [============================>.] - ETA: 0s - loss: 0.1023 - accuracy: 0.9758 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1030 - accuracy: 0.9758 - val_loss: 0.4081 - val_accuracy: 0.9237 Epoch 58/199 128/6993 [..............................] - ETA: 0s - loss: 0.0855 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0987 - accuracy: 0.9699 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0950 - accuracy: 0.9733 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0903 - accuracy: 0.9746 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0857 - accuracy: 0.9750 3456/6993 [=============>................] - ETA: 0s - loss: 0.0814 - accuracy: 0.9766 4224/6993 [=================>............] - ETA: 0s - loss: 0.0753 - accuracy: 0.9792 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0718 - accuracy: 0.9798 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0831 - accuracy: 0.9779 6784/6993 [============================>.] - ETA: 0s - loss: 0.0791 - accuracy: 0.9789 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0785 - accuracy: 0.9788 - val_loss: 0.4362 - val_accuracy: 0.9216 Epoch 59/199 128/6993 [..............................] - ETA: 0s - loss: 0.0739 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0595 - accuracy: 0.9824 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0645 - accuracy: 0.9820 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0676 - accuracy: 0.9836 3456/6993 [=============>................] - ETA: 0s - loss: 0.0700 - accuracy: 0.9815 4224/6993 [=================>............] - ETA: 0s - loss: 0.0761 - accuracy: 0.9813 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0830 - accuracy: 0.9801 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0806 - accuracy: 0.9802 6912/6993 [============================>.] - ETA: 0s - loss: 0.0898 - accuracy: 0.9786 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0890 - accuracy: 0.9787 - val_loss: 0.4289 - val_accuracy: 0.9242 Epoch 60/199 128/6993 [..............................] - ETA: 0s - loss: 0.0857 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0757 - accuracy: 0.9788 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0641 - accuracy: 0.9811 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9792 3200/6993 [============>.................] - ETA: 0s - loss: 0.0792 - accuracy: 0.9794 4096/6993 [================>.............] - ETA: 0s - loss: 0.0850 - accuracy: 0.9802 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0930 - accuracy: 0.9778 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0908 - accuracy: 0.9788 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0843 - accuracy: 0.9799 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0839 - accuracy: 0.9796 - val_loss: 0.4846 - val_accuracy: 0.9221 Epoch 61/199 128/6993 [..............................] - ETA: 0s - loss: 0.1758 - accuracy: 0.9609 768/6993 [==>...........................] - ETA: 0s - loss: 0.0760 - accuracy: 0.9805 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0653 - accuracy: 0.9826 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0745 - accuracy: 0.9786 3328/6993 [=============>................] - ETA: 0s - loss: 0.0924 - accuracy: 0.9778 4096/6993 [================>.............] - ETA: 0s - loss: 0.0888 - accuracy: 0.9780 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0920 - accuracy: 0.9776 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0938 - accuracy: 0.9762 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0886 - accuracy: 0.9772 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0890 - accuracy: 0.9773 - val_loss: 0.4608 - val_accuracy: 0.9211 Epoch 62/199 128/6993 [..............................] - ETA: 0s - loss: 0.0796 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0591 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0802 - accuracy: 0.9832 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0838 - accuracy: 0.9789 3328/6993 [=============>................] - ETA: 0s - loss: 0.0873 - accuracy: 0.9802 4224/6993 [=================>............] - ETA: 0s - loss: 0.0837 - accuracy: 0.9796 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0880 - accuracy: 0.9787 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0816 - accuracy: 0.9798 6784/6993 [============================>.] - ETA: 0s - loss: 0.0815 - accuracy: 0.9805 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0806 - accuracy: 0.9807 - val_loss: 0.4401 - val_accuracy: 0.9312 Epoch 63/199 128/6993 [..............................] - ETA: 0s - loss: 0.0720 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0924 - accuracy: 0.9833 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0990 - accuracy: 0.9771 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0783 - accuracy: 0.9805 3456/6993 [=============>................] - ETA: 0s - loss: 0.0829 - accuracy: 0.9792 4352/6993 [=================>............] - ETA: 0s - loss: 0.0834 - accuracy: 0.9798 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0855 - accuracy: 0.9781 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0833 - accuracy: 0.9782 6912/6993 [============================>.] - ETA: 0s - loss: 0.0780 - accuracy: 0.9796 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0775 - accuracy: 0.9797 - val_loss: 0.5151 - val_accuracy: 0.9196 Epoch 64/199 128/6993 [..............................] - ETA: 0s - loss: 0.0193 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0656 - accuracy: 0.9805 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0501 - accuracy: 0.9833 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0728 - accuracy: 0.9807 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0821 - accuracy: 0.9796 4352/6993 [=================>............] - ETA: 0s - loss: 0.0825 - accuracy: 0.9782 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0780 - accuracy: 0.9788 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0831 - accuracy: 0.9779 6784/6993 [============================>.] - ETA: 0s - loss: 0.0867 - accuracy: 0.9777 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0849 - accuracy: 0.9781 - val_loss: 0.4396 - val_accuracy: 0.9221 Epoch 65/199 128/6993 [..............................] - ETA: 0s - loss: 0.0370 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0396 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0654 - accuracy: 0.9820 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0796 - accuracy: 0.9828 3456/6993 [=============>................] - ETA: 0s - loss: 0.0869 - accuracy: 0.9783 4224/6993 [=================>............] - ETA: 0s - loss: 0.0827 - accuracy: 0.9775 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0780 - accuracy: 0.9777 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0713 - accuracy: 0.9796 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0700 - accuracy: 0.9803 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0688 - accuracy: 0.9807 - val_loss: 0.5297 - val_accuracy: 0.9161 Epoch 66/199 128/6993 [..............................] - ETA: 0s - loss: 0.0321 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1125 - accuracy: 0.9834 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1065 - accuracy: 0.9799 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1108 - accuracy: 0.9799 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1086 - accuracy: 0.9799 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1109 - accuracy: 0.9790 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1147 - accuracy: 0.9775 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1140 - accuracy: 0.9779 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1065 - accuracy: 0.9790 - val_loss: 0.4115 - val_accuracy: 0.9247 Epoch 67/199 128/6993 [..............................] - ETA: 0s - loss: 0.0915 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0780 - accuracy: 0.9766 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1061 - accuracy: 0.9754 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1088 - accuracy: 0.9762 3328/6993 [=============>................] - ETA: 0s - loss: 0.0954 - accuracy: 0.9775 3968/6993 [================>.............] - ETA: 0s - loss: 0.0854 - accuracy: 0.9796 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0820 - accuracy: 0.9799 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0820 - accuracy: 0.9796 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0803 - accuracy: 0.9793 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0817 - accuracy: 0.9790 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0817 - accuracy: 0.9796 - val_loss: 0.4441 - val_accuracy: 0.9226 Epoch 68/199 128/6993 [..............................] - ETA: 0s - loss: 0.0872 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0933 - accuracy: 0.9833 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0758 - accuracy: 0.9821 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0787 - accuracy: 0.9818 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0685 - accuracy: 0.9833 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0766 - accuracy: 0.9817 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0744 - accuracy: 0.9825 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0710 - accuracy: 0.9829 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0728 - accuracy: 0.9826 - val_loss: 0.4978 - val_accuracy: 0.9252 Epoch 69/199 128/6993 [..............................] - ETA: 0s - loss: 0.1836 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.1532 - accuracy: 0.9688 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1055 - accuracy: 0.9749 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0880 - accuracy: 0.9795 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0862 - accuracy: 0.9810 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0908 - accuracy: 0.9790 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0875 - accuracy: 0.9795 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0922 - accuracy: 0.9791 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0912 - accuracy: 0.9790 - val_loss: 0.4189 - val_accuracy: 0.9247 Epoch 70/199 128/6993 [..............................] - ETA: 0s - loss: 0.0087 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0679 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0928 - accuracy: 0.9849 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0881 - accuracy: 0.9833 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0748 - accuracy: 0.9844 4224/6993 [=================>............] - ETA: 0s - loss: 0.0701 - accuracy: 0.9851 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0666 - accuracy: 0.9850 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0669 - accuracy: 0.9840 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0654 - accuracy: 0.9844 6993/6993 [==============================] - 1s 77us/sample - loss: 0.0660 - accuracy: 0.9838 - val_loss: 0.4472 - val_accuracy: 0.9282 Epoch 71/199 128/6993 [..............................] - ETA: 0s - loss: 0.0546 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0509 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0560 - accuracy: 0.9838 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0482 - accuracy: 0.9866 3456/6993 [=============>................] - ETA: 0s - loss: 0.0499 - accuracy: 0.9870 4224/6993 [=================>............] - ETA: 0s - loss: 0.0501 - accuracy: 0.9860 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0551 - accuracy: 0.9858 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0665 - accuracy: 0.9844 6784/6993 [============================>.] - ETA: 0s - loss: 0.0679 - accuracy: 0.9841 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0696 - accuracy: 0.9840 - val_loss: 0.4456 - val_accuracy: 0.9232 Epoch 72/199 128/6993 [..............................] - ETA: 0s - loss: 0.1063 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0511 - accuracy: 0.9833 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0528 - accuracy: 0.9833 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0545 - accuracy: 0.9847 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0565 - accuracy: 0.9835 4224/6993 [=================>............] - ETA: 0s - loss: 0.0585 - accuracy: 0.9832 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0603 - accuracy: 0.9834 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0637 - accuracy: 0.9830 6784/6993 [============================>.] - ETA: 0s - loss: 0.0646 - accuracy: 0.9835 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0682 - accuracy: 0.9827 - val_loss: 0.4917 - val_accuracy: 0.9262 Epoch 73/199 128/6993 [..............................] - ETA: 0s - loss: 0.1093 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1205 - accuracy: 0.9814 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1050 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1195 - accuracy: 0.9810 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1007 - accuracy: 0.9821 4352/6993 [=================>............] - ETA: 0s - loss: 0.0942 - accuracy: 0.9823 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0899 - accuracy: 0.9820 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0860 - accuracy: 0.9827 6912/6993 [============================>.] - ETA: 0s - loss: 0.0863 - accuracy: 0.9822 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0854 - accuracy: 0.9824 - val_loss: 0.4911 - val_accuracy: 0.9232 Epoch 74/199 128/6993 [..............................] - ETA: 0s - loss: 0.0434 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0524 - accuracy: 0.9799 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0520 - accuracy: 0.9810 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0559 - accuracy: 0.9821 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0668 - accuracy: 0.9810 4224/6993 [=================>............] - ETA: 0s - loss: 0.0679 - accuracy: 0.9801 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0687 - accuracy: 0.9807 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0688 - accuracy: 0.9806 6784/6993 [============================>.] - ETA: 0s - loss: 0.0727 - accuracy: 0.9805 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0742 - accuracy: 0.9806 - val_loss: 0.4474 - val_accuracy: 0.9262 Epoch 75/199 128/6993 [..............................] - ETA: 0s - loss: 0.0264 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0609 - accuracy: 0.9834 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0584 - accuracy: 0.9849 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0743 - accuracy: 0.9844 3456/6993 [=============>................] - ETA: 0s - loss: 0.0787 - accuracy: 0.9832 4224/6993 [=================>............] - ETA: 0s - loss: 0.0726 - accuracy: 0.9832 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0695 - accuracy: 0.9846 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0713 - accuracy: 0.9840 6912/6993 [============================>.] - ETA: 0s - loss: 0.0757 - accuracy: 0.9835 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0760 - accuracy: 0.9831 - val_loss: 0.4730 - val_accuracy: 0.9206 Epoch 76/199 128/6993 [..............................] - ETA: 0s - loss: 0.0874 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0573 - accuracy: 0.9834 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0604 - accuracy: 0.9807 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0712 - accuracy: 0.9830 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0644 - accuracy: 0.9838 4352/6993 [=================>............] - ETA: 0s - loss: 0.0799 - accuracy: 0.9816 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0765 - accuracy: 0.9825 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0715 - accuracy: 0.9831 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0681 - accuracy: 0.9834 - val_loss: 0.4973 - val_accuracy: 0.9297 Epoch 77/199 128/6993 [..............................] - ETA: 0s - loss: 0.0397 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1036 - accuracy: 0.9785 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1032 - accuracy: 0.9802 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0980 - accuracy: 0.9811 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0860 - accuracy: 0.9827 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0794 - accuracy: 0.9827 4224/6993 [=================>............] - ETA: 0s - loss: 0.0786 - accuracy: 0.9827 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0766 - accuracy: 0.9825 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0711 - accuracy: 0.9833 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0747 - accuracy: 0.9826 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0775 - accuracy: 0.9827 - val_loss: 0.4803 - val_accuracy: 0.9257 Epoch 78/199 128/6993 [..............................] - ETA: 0s - loss: 0.1209 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0986 - accuracy: 0.9810 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0884 - accuracy: 0.9805 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0757 - accuracy: 0.9819 3328/6993 [=============>................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9826 4224/6993 [=================>............] - ETA: 0s - loss: 0.0648 - accuracy: 0.9827 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0697 - accuracy: 0.9824 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0697 - accuracy: 0.9824 6912/6993 [============================>.] - ETA: 0s - loss: 0.0797 - accuracy: 0.9802 6993/6993 [==============================] - 1s 74us/sample - loss: 0.0798 - accuracy: 0.9798 - val_loss: 0.5538 - val_accuracy: 0.9191 Epoch 79/199 128/6993 [..............................] - ETA: 0s - loss: 0.0306 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0538 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0507 - accuracy: 0.9850 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0668 - accuracy: 0.9815 3328/6993 [=============>................] - ETA: 0s - loss: 0.0626 - accuracy: 0.9820 4224/6993 [=================>............] - ETA: 0s - loss: 0.0704 - accuracy: 0.9811 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0747 - accuracy: 0.9816 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0754 - accuracy: 0.9811 6784/6993 [============================>.] - ETA: 0s - loss: 0.0787 - accuracy: 0.9810 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0783 - accuracy: 0.9811 - val_loss: 0.5347 - val_accuracy: 0.9146 Epoch 80/199 128/6993 [..............................] - ETA: 0s - loss: 0.1130 - accuracy: 0.9609 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0712 - accuracy: 0.9766 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0596 - accuracy: 0.9832 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0638 - accuracy: 0.9809 3456/6993 [=============>................] - ETA: 0s - loss: 0.0647 - accuracy: 0.9809 4224/6993 [=================>............] - ETA: 0s - loss: 0.0734 - accuracy: 0.9806 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0727 - accuracy: 0.9793 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0731 - accuracy: 0.9789 6912/6993 [============================>.] - ETA: 0s - loss: 0.0756 - accuracy: 0.9796 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0757 - accuracy: 0.9796 - val_loss: 0.4690 - val_accuracy: 0.9206 Epoch 81/199 128/6993 [..............................] - ETA: 0s - loss: 0.1451 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1053 - accuracy: 0.9766 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0832 - accuracy: 0.9818 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0807 - accuracy: 0.9858 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0851 - accuracy: 0.9852 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0828 - accuracy: 0.9839 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0762 - accuracy: 0.9842 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0712 - accuracy: 0.9844 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0699 - accuracy: 0.9840 - val_loss: 0.4798 - val_accuracy: 0.9226 Epoch 82/199 128/6993 [..............................] - ETA: 0s - loss: 0.0195 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0480 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0729 - accuracy: 0.9833 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0634 - accuracy: 0.9836 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0692 - accuracy: 0.9833 4352/6993 [=================>............] - ETA: 0s - loss: 0.0715 - accuracy: 0.9835 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0774 - accuracy: 0.9832 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0774 - accuracy: 0.9823 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0770 - accuracy: 0.9824 - val_loss: 0.5423 - val_accuracy: 0.9262 Epoch 83/199 128/6993 [..............................] - ETA: 0s - loss: 0.0633 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0606 - accuracy: 0.9831 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0733 - accuracy: 0.9832 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0725 - accuracy: 0.9832 3328/6993 [=============>................] - ETA: 0s - loss: 0.0676 - accuracy: 0.9844 4224/6993 [=================>............] - ETA: 0s - loss: 0.0706 - accuracy: 0.9834 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0739 - accuracy: 0.9818 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0773 - accuracy: 0.9817 6912/6993 [============================>.] - ETA: 0s - loss: 0.0779 - accuracy: 0.9821 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0777 - accuracy: 0.9818 - val_loss: 0.4916 - val_accuracy: 0.9226 Epoch 84/199 128/6993 [..............................] - ETA: 0s - loss: 0.0607 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0380 - accuracy: 0.9937 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0496 - accuracy: 0.9915 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0531 - accuracy: 0.9889 3328/6993 [=============>................] - ETA: 0s - loss: 0.0613 - accuracy: 0.9865 4224/6993 [=================>............] - ETA: 0s - loss: 0.0637 - accuracy: 0.9856 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0643 - accuracy: 0.9844 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0715 - accuracy: 0.9840 6784/6993 [============================>.] - ETA: 0s - loss: 0.0795 - accuracy: 0.9835 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0791 - accuracy: 0.9836 - val_loss: 0.6137 - val_accuracy: 0.9156 Epoch 85/199 128/6993 [..............................] - ETA: 0s - loss: 0.1109 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0753 - accuracy: 0.9857 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0638 - accuracy: 0.9856 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0716 - accuracy: 0.9819 3328/6993 [=============>................] - ETA: 0s - loss: 0.0638 - accuracy: 0.9829 4224/6993 [=================>............] - ETA: 0s - loss: 0.0652 - accuracy: 0.9834 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0713 - accuracy: 0.9824 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0743 - accuracy: 0.9815 6784/6993 [============================>.] - ETA: 0s - loss: 0.0811 - accuracy: 0.9807 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0833 - accuracy: 0.9807 - val_loss: 0.4840 - val_accuracy: 0.9232 Epoch 86/199 128/6993 [..............................] - ETA: 0s - loss: 0.0391 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0660 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0538 - accuracy: 0.9856 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0510 - accuracy: 0.9879 3456/6993 [=============>................] - ETA: 0s - loss: 0.0485 - accuracy: 0.9878 4352/6993 [=================>............] - ETA: 0s - loss: 0.0548 - accuracy: 0.9867 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0604 - accuracy: 0.9857 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0611 - accuracy: 0.9857 6912/6993 [============================>.] - ETA: 0s - loss: 0.0643 - accuracy: 0.9852 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0662 - accuracy: 0.9851 - val_loss: 0.6015 - val_accuracy: 0.9161 Epoch 87/199 128/6993 [..............................] - ETA: 0s - loss: 0.1581 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0749 - accuracy: 0.9855 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0779 - accuracy: 0.9850 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0776 - accuracy: 0.9825 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0727 - accuracy: 0.9833 3456/6993 [=============>................] - ETA: 0s - loss: 0.0853 - accuracy: 0.9832 4224/6993 [=================>............] - ETA: 0s - loss: 0.0780 - accuracy: 0.9844 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0793 - accuracy: 0.9836 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0863 - accuracy: 0.9827 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0869 - accuracy: 0.9823 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0847 - accuracy: 0.9823 - val_loss: 0.5362 - val_accuracy: 0.9191 Epoch 88/199 128/6993 [..............................] - ETA: 0s - loss: 0.1095 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0991 - accuracy: 0.9810 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0838 - accuracy: 0.9827 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0842 - accuracy: 0.9803 3456/6993 [=============>................] - ETA: 0s - loss: 0.0756 - accuracy: 0.9821 4352/6993 [=================>............] - ETA: 0s - loss: 0.0693 - accuracy: 0.9828 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0712 - accuracy: 0.9819 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0715 - accuracy: 0.9815 6784/6993 [============================>.] - ETA: 0s - loss: 0.0710 - accuracy: 0.9820 6993/6993 [==============================] - 1s 77us/sample - loss: 0.0708 - accuracy: 0.9823 - val_loss: 0.4979 - val_accuracy: 0.9247 Epoch 89/199 128/6993 [..............................] - ETA: 0s - loss: 0.0282 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0503 - accuracy: 0.9883 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0607 - accuracy: 0.9849 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0629 - accuracy: 0.9851 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0661 - accuracy: 0.9841 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0798 - accuracy: 0.9815 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0814 - accuracy: 0.9807 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0815 - accuracy: 0.9801 6912/6993 [============================>.] - ETA: 0s - loss: 0.0768 - accuracy: 0.9809 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0762 - accuracy: 0.9810 - val_loss: 0.4458 - val_accuracy: 0.9317 Epoch 90/199 128/6993 [..............................] - ETA: 0s - loss: 0.1243 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0494 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0481 - accuracy: 0.9860 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0620 - accuracy: 0.9867 3456/6993 [=============>................] - ETA: 0s - loss: 0.0630 - accuracy: 0.9855 4352/6993 [=================>............] - ETA: 0s - loss: 0.0611 - accuracy: 0.9851 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0699 - accuracy: 0.9842 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0684 - accuracy: 0.9849 6784/6993 [============================>.] - ETA: 0s - loss: 0.0697 - accuracy: 0.9845 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0686 - accuracy: 0.9844 - val_loss: 0.4886 - val_accuracy: 0.9338 Epoch 91/199 128/6993 [..............................] - ETA: 0s - loss: 0.0040 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0364 - accuracy: 0.9911 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0629 - accuracy: 0.9855 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0690 - accuracy: 0.9825 3456/6993 [=============>................] - ETA: 0s - loss: 0.0628 - accuracy: 0.9841 4352/6993 [=================>............] - ETA: 0s - loss: 0.0793 - accuracy: 0.9841 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0784 - accuracy: 0.9842 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0749 - accuracy: 0.9842 6784/6993 [============================>.] - ETA: 0s - loss: 0.0778 - accuracy: 0.9833 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0773 - accuracy: 0.9834 - val_loss: 0.4951 - val_accuracy: 0.9257 Epoch 92/199 128/6993 [..............................] - ETA: 0s - loss: 0.0403 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0580 - accuracy: 0.9911 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0652 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0733 - accuracy: 0.9829 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0719 - accuracy: 0.9824 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0806 - accuracy: 0.9815 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0771 - accuracy: 0.9824 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0789 - accuracy: 0.9827 6784/6993 [============================>.] - ETA: 0s - loss: 0.0774 - accuracy: 0.9832 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0764 - accuracy: 0.9834 - val_loss: 0.5475 - val_accuracy: 0.9186 Epoch 93/199 128/6993 [..............................] - ETA: 0s - loss: 0.0209 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0628 - accuracy: 0.9893 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0738 - accuracy: 0.9833 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0837 - accuracy: 0.9803 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0751 - accuracy: 0.9824 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0668 - accuracy: 0.9842 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0729 - accuracy: 0.9846 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0692 - accuracy: 0.9852 6912/6993 [============================>.] - ETA: 0s - loss: 0.0664 - accuracy: 0.9858 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0662 - accuracy: 0.9858 - val_loss: 0.5339 - val_accuracy: 0.9257 Epoch 94/199 128/6993 [..............................] - ETA: 0s - loss: 0.0349 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0623 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0637 - accuracy: 0.9849 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0628 - accuracy: 0.9867 3456/6993 [=============>................] - ETA: 0s - loss: 0.0688 - accuracy: 0.9850 4352/6993 [=================>............] - ETA: 0s - loss: 0.0743 - accuracy: 0.9862 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0691 - accuracy: 0.9862 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0697 - accuracy: 0.9862 6784/6993 [============================>.] - ETA: 0s - loss: 0.0778 - accuracy: 0.9853 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0762 - accuracy: 0.9854 - val_loss: 0.5374 - val_accuracy: 0.9252 Epoch 95/199 128/6993 [..............................] - ETA: 0s - loss: 0.0412 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0675 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0730 - accuracy: 0.9826 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0625 - accuracy: 0.9848 3456/6993 [=============>................] - ETA: 0s - loss: 0.0628 - accuracy: 0.9850 4352/6993 [=================>............] - ETA: 0s - loss: 0.0684 - accuracy: 0.9848 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0756 - accuracy: 0.9840 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0800 - accuracy: 0.9836 6912/6993 [============================>.] - ETA: 0s - loss: 0.0801 - accuracy: 0.9831 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0801 - accuracy: 0.9828 - val_loss: 0.4807 - val_accuracy: 0.9242 Epoch 96/199 128/6993 [..............................] - ETA: 0s - loss: 0.0324 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0313 - accuracy: 0.9883 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0452 - accuracy: 0.9862 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0744 - accuracy: 0.9809 3456/6993 [=============>................] - ETA: 0s - loss: 0.0694 - accuracy: 0.9823 4096/6993 [================>.............] - ETA: 0s - loss: 0.0628 - accuracy: 0.9836 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0625 - accuracy: 0.9844 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0579 - accuracy: 0.9853 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0635 - accuracy: 0.9841 6784/6993 [============================>.] - ETA: 0s - loss: 0.0669 - accuracy: 0.9844 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0670 - accuracy: 0.9844 - val_loss: 0.5384 - val_accuracy: 0.9221 Epoch 97/199 128/6993 [..............................] - ETA: 0s - loss: 0.1610 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0939 - accuracy: 0.9810 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0784 - accuracy: 0.9862 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0759 - accuracy: 0.9858 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0792 - accuracy: 0.9837 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0795 - accuracy: 0.9833 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0743 - accuracy: 0.9835 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0777 - accuracy: 0.9830 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0776 - accuracy: 0.9830 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0791 - accuracy: 0.9823 - val_loss: 0.5579 - val_accuracy: 0.9247 Epoch 98/199 128/6993 [..............................] - ETA: 0s - loss: 0.0559 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0736 - accuracy: 0.9834 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0828 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0719 - accuracy: 0.9852 3456/6993 [=============>................] - ETA: 0s - loss: 0.0779 - accuracy: 0.9841 4352/6993 [=================>............] - ETA: 0s - loss: 0.0736 - accuracy: 0.9839 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0814 - accuracy: 0.9842 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0835 - accuracy: 0.9834 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0801 - accuracy: 0.9843 - val_loss: 0.5390 - val_accuracy: 0.9277 Epoch 99/199 128/6993 [..............................] - ETA: 0s - loss: 0.0383 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0415 - accuracy: 0.9863 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0571 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0556 - accuracy: 0.9844 3456/6993 [=============>................] - ETA: 0s - loss: 0.0669 - accuracy: 0.9847 4352/6993 [=================>............] - ETA: 0s - loss: 0.0622 - accuracy: 0.9846 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0631 - accuracy: 0.9846 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0662 - accuracy: 0.9842 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0648 - accuracy: 0.9844 - val_loss: 0.5082 - val_accuracy: 0.9221 Epoch 100/199 128/6993 [..............................] - ETA: 0s - loss: 0.0415 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0578 - accuracy: 0.9912 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0689 - accuracy: 0.9859 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0615 - accuracy: 0.9852 3456/6993 [=============>................] - ETA: 0s - loss: 0.0656 - accuracy: 0.9844 4352/6993 [=================>............] - ETA: 0s - loss: 0.0644 - accuracy: 0.9844 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0751 - accuracy: 0.9840 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0737 - accuracy: 0.9837 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0755 - accuracy: 0.9838 - val_loss: 0.5141 - val_accuracy: 0.9272 Epoch 101/199 128/6993 [..............................] - ETA: 0s - loss: 0.0096 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0611 - accuracy: 0.9854 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0907 - accuracy: 0.9810 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0923 - accuracy: 0.9809 3328/6993 [=============>................] - ETA: 0s - loss: 0.0874 - accuracy: 0.9814 4224/6993 [=================>............] - ETA: 0s - loss: 0.0819 - accuracy: 0.9830 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0785 - accuracy: 0.9838 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0739 - accuracy: 0.9850 6912/6993 [============================>.] - ETA: 0s - loss: 0.0734 - accuracy: 0.9848 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0729 - accuracy: 0.9847 - val_loss: 0.5042 - val_accuracy: 0.9262 Epoch 102/199 128/6993 [..............................] - ETA: 0s - loss: 0.0477 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0621 - accuracy: 0.9805 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0859 - accuracy: 0.9792 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0906 - accuracy: 0.9798 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0971 - accuracy: 0.9814 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0925 - accuracy: 0.9813 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0958 - accuracy: 0.9816 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0927 - accuracy: 0.9817 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0876 - accuracy: 0.9821 - val_loss: 0.5530 - val_accuracy: 0.9186 Epoch 103/199 128/6993 [..............................] - ETA: 0s - loss: 0.1442 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0444 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0452 - accuracy: 0.9886 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0558 - accuracy: 0.9885 3328/6993 [=============>................] - ETA: 0s - loss: 0.0611 - accuracy: 0.9871 4096/6993 [================>.............] - ETA: 0s - loss: 0.0580 - accuracy: 0.9873 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0604 - accuracy: 0.9866 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0625 - accuracy: 0.9866 6784/6993 [============================>.] - ETA: 0s - loss: 0.0670 - accuracy: 0.9872 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0660 - accuracy: 0.9874 - val_loss: 0.5600 - val_accuracy: 0.9267 Epoch 104/199 128/6993 [..............................] - ETA: 0s - loss: 0.0170 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0710 - accuracy: 0.9833 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0705 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0588 - accuracy: 0.9855 3328/6993 [=============>................] - ETA: 0s - loss: 0.0568 - accuracy: 0.9853 4224/6993 [=================>............] - ETA: 0s - loss: 0.0649 - accuracy: 0.9841 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0659 - accuracy: 0.9846 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0725 - accuracy: 0.9837 6912/6993 [============================>.] - ETA: 0s - loss: 0.0714 - accuracy: 0.9842 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0715 - accuracy: 0.9841 - val_loss: 0.4952 - val_accuracy: 0.9242 Epoch 105/199 128/6993 [..............................] - ETA: 0s - loss: 0.0582 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0595 - accuracy: 0.9854 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0788 - accuracy: 0.9814 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0762 - accuracy: 0.9815 3328/6993 [=============>................] - ETA: 0s - loss: 0.0676 - accuracy: 0.9826 4224/6993 [=================>............] - ETA: 0s - loss: 0.0653 - accuracy: 0.9844 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0658 - accuracy: 0.9842 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0673 - accuracy: 0.9835 6912/6993 [============================>.] - ETA: 0s - loss: 0.0668 - accuracy: 0.9838 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0678 - accuracy: 0.9837 - val_loss: 0.4957 - val_accuracy: 0.9191 Epoch 106/199 128/6993 [..............................] - ETA: 0s - loss: 0.1285 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0480 - accuracy: 0.9873 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0556 - accuracy: 0.9891 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0709 - accuracy: 0.9858 3456/6993 [=============>................] - ETA: 0s - loss: 0.0837 - accuracy: 0.9850 4224/6993 [=================>............] - ETA: 0s - loss: 0.0848 - accuracy: 0.9846 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0849 - accuracy: 0.9844 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0845 - accuracy: 0.9846 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0838 - accuracy: 0.9842 6784/6993 [============================>.] - ETA: 0s - loss: 0.0830 - accuracy: 0.9838 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0835 - accuracy: 0.9837 - val_loss: 0.5122 - val_accuracy: 0.9221 Epoch 107/199 128/6993 [..............................] - ETA: 0s - loss: 0.1263 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0525 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0516 - accuracy: 0.9849 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0443 - accuracy: 0.9877 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0544 - accuracy: 0.9866 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0598 - accuracy: 0.9866 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0610 - accuracy: 0.9868 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0569 - accuracy: 0.9876 6912/6993 [============================>.] - ETA: 0s - loss: 0.0632 - accuracy: 0.9870 6993/6993 [==============================] - 1s 77us/sample - loss: 0.0626 - accuracy: 0.9871 - val_loss: 0.5737 - val_accuracy: 0.9211 Epoch 108/199 128/6993 [..............................] - ETA: 0s - loss: 0.0277 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0300 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0427 - accuracy: 0.9894 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0456 - accuracy: 0.9900 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0614 - accuracy: 0.9863 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0652 - accuracy: 0.9862 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0644 - accuracy: 0.9853 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0712 - accuracy: 0.9841 6993/6993 [==============================] - 1s 74us/sample - loss: 0.0694 - accuracy: 0.9846 - val_loss: 0.5368 - val_accuracy: 0.9292 Epoch 109/199 128/6993 [..............................] - ETA: 0s - loss: 0.0053 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0446 - accuracy: 0.9933 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0818 - accuracy: 0.9900 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0615 - accuracy: 0.9900 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0806 - accuracy: 0.9877 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0764 - accuracy: 0.9866 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0745 - accuracy: 0.9864 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0736 - accuracy: 0.9863 6912/6993 [============================>.] - ETA: 0s - loss: 0.0716 - accuracy: 0.9864 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0713 - accuracy: 0.9863 - val_loss: 0.5508 - val_accuracy: 0.9252 Epoch 110/199 128/6993 [..............................] - ETA: 0s - loss: 0.1315 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0584 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0448 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0567 - accuracy: 0.9862 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0616 - accuracy: 0.9860 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0710 - accuracy: 0.9855 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0700 - accuracy: 0.9855 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0713 - accuracy: 0.9842 6912/6993 [============================>.] - ETA: 0s - loss: 0.0699 - accuracy: 0.9842 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0693 - accuracy: 0.9844 - val_loss: 0.5254 - val_accuracy: 0.9237 Epoch 111/199 128/6993 [..............................] - ETA: 0s - loss: 0.0114 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0326 - accuracy: 0.9933 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0337 - accuracy: 0.9927 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0350 - accuracy: 0.9922 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0425 - accuracy: 0.9911 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0452 - accuracy: 0.9913 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0425 - accuracy: 0.9914 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0469 - accuracy: 0.9900 6993/6993 [==============================] - 1s 74us/sample - loss: 0.0573 - accuracy: 0.9888 - val_loss: 0.5530 - val_accuracy: 0.9247 Epoch 112/199 128/6993 [..............................] - ETA: 0s - loss: 0.1030 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0604 - accuracy: 0.9844 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0641 - accuracy: 0.9849 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0632 - accuracy: 0.9858 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0734 - accuracy: 0.9863 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0731 - accuracy: 0.9855 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0729 - accuracy: 0.9853 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0780 - accuracy: 0.9844 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0747 - accuracy: 0.9844 - val_loss: 0.6410 - val_accuracy: 0.9237 Epoch 113/199 128/6993 [..............................] - ETA: 0s - loss: 0.1309 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0625 - accuracy: 0.9902 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0950 - accuracy: 0.9875 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0923 - accuracy: 0.9865 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0905 - accuracy: 0.9855 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0832 - accuracy: 0.9852 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0763 - accuracy: 0.9853 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0777 - accuracy: 0.9855 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0774 - accuracy: 0.9858 - val_loss: 0.5719 - val_accuracy: 0.9232 Epoch 114/199 128/6993 [..............................] - ETA: 0s - loss: 0.0190 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0851 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0646 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0588 - accuracy: 0.9888 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0678 - accuracy: 0.9874 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0673 - accuracy: 0.9879 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0755 - accuracy: 0.9862 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0765 - accuracy: 0.9860 6912/6993 [============================>.] - ETA: 0s - loss: 0.0761 - accuracy: 0.9861 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0758 - accuracy: 0.9861 - val_loss: 0.5505 - val_accuracy: 0.9257 Epoch 115/199 128/6993 [..............................] - ETA: 0s - loss: 0.0340 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0361 - accuracy: 0.9883 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0331 - accuracy: 0.9880 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0400 - accuracy: 0.9855 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0632 - accuracy: 0.9838 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0648 - accuracy: 0.9835 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0671 - accuracy: 0.9833 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0652 - accuracy: 0.9841 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0685 - accuracy: 0.9844 - val_loss: 0.6221 - val_accuracy: 0.9216 Epoch 116/199 128/6993 [..............................] - ETA: 0s - loss: 0.0639 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0769 - accuracy: 0.9792 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0611 - accuracy: 0.9826 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0614 - accuracy: 0.9860 3072/6993 [============>.................] - ETA: 0s - loss: 0.0643 - accuracy: 0.9854 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0783 - accuracy: 0.9838 4352/6993 [=================>............] - ETA: 0s - loss: 0.0743 - accuracy: 0.9841 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0743 - accuracy: 0.9844 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0745 - accuracy: 0.9842 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0773 - accuracy: 0.9829 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0766 - accuracy: 0.9828 - val_loss: 0.5445 - val_accuracy: 0.9292 Epoch 117/199 128/6993 [..............................] - ETA: 0s - loss: 0.0133 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0450 - accuracy: 0.9854 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0565 - accuracy: 0.9833 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0824 - accuracy: 0.9830 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0806 - accuracy: 0.9833 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0808 - accuracy: 0.9835 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0787 - accuracy: 0.9833 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0821 - accuracy: 0.9829 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0939 - accuracy: 0.9820 - val_loss: 0.5134 - val_accuracy: 0.9247 Epoch 118/199 128/6993 [..............................] - ETA: 0s - loss: 0.0890 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0630 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0782 - accuracy: 0.9810 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0664 - accuracy: 0.9833 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0744 - accuracy: 0.9807 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0690 - accuracy: 0.9821 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0640 - accuracy: 0.9833 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0641 - accuracy: 0.9839 6993/6993 [==============================] - 1s 74us/sample - loss: 0.0658 - accuracy: 0.9837 - val_loss: 0.4449 - val_accuracy: 0.9348 Epoch 119/199 128/6993 [..............................] - ETA: 0s - loss: 0.0296 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0503 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0490 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0550 - accuracy: 0.9881 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0494 - accuracy: 0.9891 4224/6993 [=================>............] - ETA: 0s - loss: 0.0621 - accuracy: 0.9882 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0569 - accuracy: 0.9885 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0517 - accuracy: 0.9885 6784/6993 [============================>.] - ETA: 0s - loss: 0.0617 - accuracy: 0.9873 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0609 - accuracy: 0.9874 - val_loss: 0.6211 - val_accuracy: 0.9216 Epoch 120/199 128/6993 [..............................] - ETA: 0s - loss: 0.1176 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0463 - accuracy: 0.9893 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0473 - accuracy: 0.9880 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0420 - accuracy: 0.9890 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0392 - accuracy: 0.9894 4352/6993 [=================>............] - ETA: 0s - loss: 0.0435 - accuracy: 0.9883 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0531 - accuracy: 0.9887 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0634 - accuracy: 0.9874 6912/6993 [============================>.] - ETA: 0s - loss: 0.0601 - accuracy: 0.9880 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0601 - accuracy: 0.9878 - val_loss: 0.5823 - val_accuracy: 0.9247 Epoch 121/199 128/6993 [..............................] - ETA: 0s - loss: 0.2188 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0689 - accuracy: 0.9824 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0590 - accuracy: 0.9828 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0628 - accuracy: 0.9840 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0592 - accuracy: 0.9849 4352/6993 [=================>............] - ETA: 0s - loss: 0.0651 - accuracy: 0.9846 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0808 - accuracy: 0.9840 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0754 - accuracy: 0.9849 6912/6993 [============================>.] - ETA: 0s - loss: 0.0724 - accuracy: 0.9855 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0720 - accuracy: 0.9856 - val_loss: 0.5790 - val_accuracy: 0.9312 Epoch 122/199 128/6993 [..............................] - ETA: 0s - loss: 0.0306 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0712 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0818 - accuracy: 0.9849 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0773 - accuracy: 0.9870 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0770 - accuracy: 0.9863 4224/6993 [=================>............] - ETA: 0s - loss: 0.0782 - accuracy: 0.9865 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0712 - accuracy: 0.9864 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0761 - accuracy: 0.9861 6784/6993 [============================>.] - ETA: 0s - loss: 0.0704 - accuracy: 0.9861 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0693 - accuracy: 0.9861 - val_loss: 0.5672 - val_accuracy: 0.9292 Epoch 123/199 128/6993 [..............................] - ETA: 0s - loss: 0.0061 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0857 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1043 - accuracy: 0.9838 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0967 - accuracy: 0.9836 3456/6993 [=============>................] - ETA: 0s - loss: 0.0916 - accuracy: 0.9838 4224/6993 [=================>............] - ETA: 0s - loss: 0.0882 - accuracy: 0.9844 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0792 - accuracy: 0.9850 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0747 - accuracy: 0.9854 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0721 - accuracy: 0.9861 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0703 - accuracy: 0.9860 - val_loss: 0.5663 - val_accuracy: 0.9317 Epoch 124/199 128/6993 [..............................] - ETA: 0s - loss: 0.0461 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0970 - accuracy: 0.9870 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0814 - accuracy: 0.9824 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0653 - accuracy: 0.9835 3072/6993 [============>.................] - ETA: 0s - loss: 0.0656 - accuracy: 0.9844 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0682 - accuracy: 0.9849 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0686 - accuracy: 0.9844 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0750 - accuracy: 0.9838 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0748 - accuracy: 0.9844 6784/6993 [============================>.] - ETA: 0s - loss: 0.0719 - accuracy: 0.9841 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0705 - accuracy: 0.9843 - val_loss: 0.6596 - val_accuracy: 0.9292 Epoch 125/199 128/6993 [..............................] - ETA: 0s - loss: 0.0341 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0763 - accuracy: 0.9855 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0606 - accuracy: 0.9862 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0597 - accuracy: 0.9868 3328/6993 [=============>................] - ETA: 0s - loss: 0.0594 - accuracy: 0.9853 4224/6993 [=================>............] - ETA: 0s - loss: 0.0548 - accuracy: 0.9860 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0494 - accuracy: 0.9867 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0623 - accuracy: 0.9862 6912/6993 [============================>.] - ETA: 0s - loss: 0.0613 - accuracy: 0.9857 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0609 - accuracy: 0.9857 - val_loss: 0.6410 - val_accuracy: 0.9272 Epoch 126/199 128/6993 [..............................] - ETA: 0s - loss: 0.2277 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0758 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0462 - accuracy: 0.9893 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0539 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0665 - accuracy: 0.9881 3328/6993 [=============>................] - ETA: 0s - loss: 0.0724 - accuracy: 0.9865 3968/6993 [================>.............] - ETA: 0s - loss: 0.0685 - accuracy: 0.9869 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0654 - accuracy: 0.9872 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0638 - accuracy: 0.9872 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0686 - accuracy: 0.9867 6912/6993 [============================>.] - ETA: 0s - loss: 0.0665 - accuracy: 0.9865 6993/6993 [==============================] - 1s 99us/sample - loss: 0.0658 - accuracy: 0.9867 - val_loss: 0.5721 - val_accuracy: 0.9282 Epoch 127/199 128/6993 [..............................] - ETA: 0s - loss: 0.0043 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0325 - accuracy: 0.9922 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0721 - accuracy: 0.9849 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0636 - accuracy: 0.9854 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0709 - accuracy: 0.9865 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0780 - accuracy: 0.9868 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0874 - accuracy: 0.9864 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0803 - accuracy: 0.9869 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0821 - accuracy: 0.9867 - val_loss: 0.5147 - val_accuracy: 0.9257 Epoch 128/199 128/6993 [..............................] - ETA: 0s - loss: 0.0021 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0278 - accuracy: 0.9941 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0576 - accuracy: 0.9896 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0795 - accuracy: 0.9886 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0756 - accuracy: 0.9876 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0738 - accuracy: 0.9876 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0779 - accuracy: 0.9873 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0795 - accuracy: 0.9867 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0866 - accuracy: 0.9864 - val_loss: 0.5002 - val_accuracy: 0.9287 Epoch 129/199 128/6993 [..............................] - ETA: 0s - loss: 0.0698 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0554 - accuracy: 0.9844 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0490 - accuracy: 0.9844 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0437 - accuracy: 0.9879 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0616 - accuracy: 0.9868 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0609 - accuracy: 0.9863 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0673 - accuracy: 0.9860 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0660 - accuracy: 0.9864 6993/6993 [==============================] - 1s 75us/sample - loss: 0.0659 - accuracy: 0.9860 - val_loss: 0.5224 - val_accuracy: 0.9338 Epoch 130/199 128/6993 [..............................] - ETA: 0s - loss: 0.0428 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0721 - accuracy: 0.9883 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0606 - accuracy: 0.9885 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0671 - accuracy: 0.9872 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0665 - accuracy: 0.9860 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0685 - accuracy: 0.9859 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0712 - accuracy: 0.9851 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0692 - accuracy: 0.9853 6993/6993 [==============================] - 1s 77us/sample - loss: 0.0662 - accuracy: 0.9857 - val_loss: 0.5448 - val_accuracy: 0.9312 Epoch 131/199 128/6993 [..............................] - ETA: 0s - loss: 0.0216 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0293 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0484 - accuracy: 0.9894 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0478 - accuracy: 0.9903 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0491 - accuracy: 0.9902 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0584 - accuracy: 0.9891 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0634 - accuracy: 0.9877 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0656 - accuracy: 0.9868 6912/6993 [============================>.] - ETA: 0s - loss: 0.0643 - accuracy: 0.9871 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0637 - accuracy: 0.9873 - val_loss: 0.5240 - val_accuracy: 0.9373 Epoch 132/199 128/6993 [..............................] - ETA: 0s - loss: 0.0846 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1250 - accuracy: 0.9893 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1481 - accuracy: 0.9875 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1091 - accuracy: 0.9886 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0927 - accuracy: 0.9891 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0906 - accuracy: 0.9875 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0954 - accuracy: 0.9868 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0947 - accuracy: 0.9861 6912/6993 [============================>.] - ETA: 0s - loss: 0.0897 - accuracy: 0.9864 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0888 - accuracy: 0.9864 - val_loss: 0.5562 - val_accuracy: 0.9282 Epoch 133/199 128/6993 [..............................] - ETA: 0s - loss: 0.1397 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0594 - accuracy: 0.9900 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0571 - accuracy: 0.9888 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0581 - accuracy: 0.9883 3456/6993 [=============>................] - ETA: 0s - loss: 0.0486 - accuracy: 0.9899 4352/6993 [=================>............] - ETA: 0s - loss: 0.0566 - accuracy: 0.9897 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0659 - accuracy: 0.9883 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0649 - accuracy: 0.9879 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0641 - accuracy: 0.9877 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0680 - accuracy: 0.9877 - val_loss: 0.5657 - val_accuracy: 0.9277 Epoch 134/199 128/6993 [..............................] - ETA: 0s - loss: 0.0322 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0357 - accuracy: 0.9902 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0419 - accuracy: 0.9885 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0501 - accuracy: 0.9876 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0523 - accuracy: 0.9868 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0491 - accuracy: 0.9872 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0553 - accuracy: 0.9868 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0707 - accuracy: 0.9853 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0711 - accuracy: 0.9850 - val_loss: 0.5075 - val_accuracy: 0.9282 Epoch 135/199 128/6993 [..............................] - ETA: 0s - loss: 0.0261 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0353 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0357 - accuracy: 0.9877 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0430 - accuracy: 0.9870 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0444 - accuracy: 0.9869 4352/6993 [=================>............] - ETA: 0s - loss: 0.0416 - accuracy: 0.9869 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0482 - accuracy: 0.9869 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0480 - accuracy: 0.9870 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0550 - accuracy: 0.9864 6912/6993 [============================>.] - ETA: 0s - loss: 0.0555 - accuracy: 0.9864 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0549 - accuracy: 0.9866 - val_loss: 0.6904 - val_accuracy: 0.9226 Epoch 136/199 128/6993 [..............................] - ETA: 0s - loss: 0.1315 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1754 - accuracy: 0.9870 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1188 - accuracy: 0.9902 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0968 - accuracy: 0.9903 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0847 - accuracy: 0.9898 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0745 - accuracy: 0.9898 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0703 - accuracy: 0.9893 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0688 - accuracy: 0.9889 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0691 - accuracy: 0.9885 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0714 - accuracy: 0.9878 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0699 - accuracy: 0.9881 - val_loss: 0.6338 - val_accuracy: 0.9292 Epoch 137/199 128/6993 [..............................] - ETA: 0s - loss: 0.0080 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0835 - accuracy: 0.9857 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0634 - accuracy: 0.9870 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0742 - accuracy: 0.9852 3200/6993 [============>.................] - ETA: 0s - loss: 0.0807 - accuracy: 0.9847 3968/6993 [================>.............] - ETA: 0s - loss: 0.0885 - accuracy: 0.9831 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0893 - accuracy: 0.9831 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0846 - accuracy: 0.9839 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0788 - accuracy: 0.9850 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0815 - accuracy: 0.9848 - val_loss: 0.5806 - val_accuracy: 0.9317 Epoch 138/199 128/6993 [..............................] - ETA: 0s - loss: 0.0174 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0325 - accuracy: 0.9935 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0384 - accuracy: 0.9929 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0432 - accuracy: 0.9907 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0524 - accuracy: 0.9892 3328/6993 [=============>................] - ETA: 0s - loss: 0.0650 - accuracy: 0.9877 3968/6993 [================>.............] - ETA: 0s - loss: 0.0614 - accuracy: 0.9877 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0638 - accuracy: 0.9875 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0579 - accuracy: 0.9885 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0651 - accuracy: 0.9886 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0633 - accuracy: 0.9887 - val_loss: 0.6074 - val_accuracy: 0.9267 Epoch 139/199 128/6993 [..............................] - ETA: 0s - loss: 0.1343 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0680 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0571 - accuracy: 0.9872 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0554 - accuracy: 0.9859 3328/6993 [=============>................] - ETA: 0s - loss: 0.0509 - accuracy: 0.9874 4224/6993 [=================>............] - ETA: 0s - loss: 0.0509 - accuracy: 0.9882 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0505 - accuracy: 0.9882 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0504 - accuracy: 0.9885 6784/6993 [============================>.] - ETA: 0s - loss: 0.0631 - accuracy: 0.9864 6993/6993 [==============================] - 1s 77us/sample - loss: 0.0642 - accuracy: 0.9857 - val_loss: 0.6097 - val_accuracy: 0.9226 Epoch 140/199 128/6993 [..............................] - ETA: 0s - loss: 0.0434 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0253 - accuracy: 0.9951 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0455 - accuracy: 0.9932 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0473 - accuracy: 0.9922 3456/6993 [=============>................] - ETA: 0s - loss: 0.0658 - accuracy: 0.9902 4352/6993 [=================>............] - ETA: 0s - loss: 0.0660 - accuracy: 0.9883 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0612 - accuracy: 0.9876 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0580 - accuracy: 0.9878 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0573 - accuracy: 0.9883 - val_loss: 0.6463 - val_accuracy: 0.9277 Epoch 141/199 128/6993 [..............................] - ETA: 0s - loss: 0.1279 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0622 - accuracy: 0.9873 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0500 - accuracy: 0.9894 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0522 - accuracy: 0.9891 3200/6993 [============>.................] - ETA: 0s - loss: 0.0507 - accuracy: 0.9894 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0568 - accuracy: 0.9888 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0518 - accuracy: 0.9893 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0513 - accuracy: 0.9896 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0554 - accuracy: 0.9899 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0671 - accuracy: 0.9883 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0688 - accuracy: 0.9876 - val_loss: 0.6457 - val_accuracy: 0.9277 Epoch 142/199 128/6993 [..............................] - ETA: 0s - loss: 0.0530 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0723 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0622 - accuracy: 0.9868 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0565 - accuracy: 0.9879 3200/6993 [============>.................] - ETA: 0s - loss: 0.0608 - accuracy: 0.9862 3968/6993 [================>.............] - ETA: 0s - loss: 0.0623 - accuracy: 0.9859 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0576 - accuracy: 0.9868 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0573 - accuracy: 0.9868 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0616 - accuracy: 0.9865 6912/6993 [============================>.] - ETA: 0s - loss: 0.0578 - accuracy: 0.9870 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0574 - accuracy: 0.9870 - val_loss: 0.5967 - val_accuracy: 0.9272 Epoch 143/199 128/6993 [..............................] - ETA: 0s - loss: 0.0297 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0394 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0624 - accuracy: 0.9866 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0663 - accuracy: 0.9863 3456/6993 [=============>................] - ETA: 0s - loss: 0.0694 - accuracy: 0.9873 4224/6993 [=================>............] - ETA: 0s - loss: 0.0729 - accuracy: 0.9870 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0712 - accuracy: 0.9865 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0753 - accuracy: 0.9851 6784/6993 [============================>.] - ETA: 0s - loss: 0.0847 - accuracy: 0.9836 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0823 - accuracy: 0.9841 - val_loss: 0.5249 - val_accuracy: 0.9257 Epoch 144/199 128/6993 [..............................] - ETA: 0s - loss: 0.0180 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0504 - accuracy: 0.9821 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0520 - accuracy: 0.9821 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0447 - accuracy: 0.9859 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0436 - accuracy: 0.9847 4352/6993 [=================>............] - ETA: 0s - loss: 0.0468 - accuracy: 0.9853 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0593 - accuracy: 0.9857 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0559 - accuracy: 0.9863 6912/6993 [============================>.] - ETA: 0s - loss: 0.0570 - accuracy: 0.9863 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0583 - accuracy: 0.9861 - val_loss: 0.7239 - val_accuracy: 0.9206 Epoch 145/199 128/6993 [..............................] - ETA: 0s - loss: 0.0043 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0741 - accuracy: 0.9909 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0477 - accuracy: 0.9937 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0626 - accuracy: 0.9905 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0624 - accuracy: 0.9893 3072/6993 [============>.................] - ETA: 0s - loss: 0.0543 - accuracy: 0.9906 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0669 - accuracy: 0.9892 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0764 - accuracy: 0.9875 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0712 - accuracy: 0.9870 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0734 - accuracy: 0.9866 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0761 - accuracy: 0.9864 - val_loss: 0.5638 - val_accuracy: 0.9221 Epoch 146/199 128/6993 [..............................] - ETA: 0s - loss: 0.1135 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0514 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0526 - accuracy: 0.9877 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0506 - accuracy: 0.9877 3456/6993 [=============>................] - ETA: 0s - loss: 0.0431 - accuracy: 0.9887 4352/6993 [=================>............] - ETA: 0s - loss: 0.0486 - accuracy: 0.9892 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0525 - accuracy: 0.9893 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0497 - accuracy: 0.9900 6912/6993 [============================>.] - ETA: 0s - loss: 0.0527 - accuracy: 0.9899 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0536 - accuracy: 0.9898 - val_loss: 0.6525 - val_accuracy: 0.9252 Epoch 147/199 128/6993 [..............................] - ETA: 0s - loss: 0.1277 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0739 - accuracy: 0.9883 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0553 - accuracy: 0.9891 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0711 - accuracy: 0.9865 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0738 - accuracy: 0.9863 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0789 - accuracy: 0.9862 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0743 - accuracy: 0.9853 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0684 - accuracy: 0.9861 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0676 - accuracy: 0.9870 - val_loss: 0.6759 - val_accuracy: 0.9282 Epoch 148/199 128/6993 [..............................] - ETA: 0s - loss: 0.0081 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0726 - accuracy: 0.9896 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0733 - accuracy: 0.9902 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0605 - accuracy: 0.9885 3328/6993 [=============>................] - ETA: 0s - loss: 0.0915 - accuracy: 0.9856 4096/6993 [================>.............] - ETA: 0s - loss: 0.1084 - accuracy: 0.9851 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1184 - accuracy: 0.9842 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1107 - accuracy: 0.9847 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0986 - accuracy: 0.9863 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0971 - accuracy: 0.9863 - val_loss: 0.5875 - val_accuracy: 0.9237 Epoch 149/199 128/6993 [..............................] - ETA: 0s - loss: 0.0334 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0442 - accuracy: 0.9863 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0464 - accuracy: 0.9894 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0767 - accuracy: 0.9866 3456/6993 [=============>................] - ETA: 0s - loss: 0.0674 - accuracy: 0.9878 4224/6993 [=================>............] - ETA: 0s - loss: 0.0759 - accuracy: 0.9867 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0721 - accuracy: 0.9859 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0756 - accuracy: 0.9869 6784/6993 [============================>.] - ETA: 0s - loss: 0.0786 - accuracy: 0.9869 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0775 - accuracy: 0.9868 - val_loss: 0.5564 - val_accuracy: 0.9237 Epoch 150/199 128/6993 [..............................] - ETA: 0s - loss: 0.0117 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0826 - accuracy: 0.9844 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0727 - accuracy: 0.9844 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0649 - accuracy: 0.9848 3200/6993 [============>.................] - ETA: 0s - loss: 0.0524 - accuracy: 0.9872 3968/6993 [================>.............] - ETA: 0s - loss: 0.0499 - accuracy: 0.9877 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0504 - accuracy: 0.9873 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0493 - accuracy: 0.9874 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0488 - accuracy: 0.9874 6784/6993 [============================>.] - ETA: 0s - loss: 0.0482 - accuracy: 0.9876 6993/6993 [==============================] - 1s 97us/sample - loss: 0.0477 - accuracy: 0.9876 - val_loss: 0.5954 - val_accuracy: 0.9312 Epoch 151/199 128/6993 [..............................] - ETA: 0s - loss: 0.0544 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0683 - accuracy: 0.9857 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0590 - accuracy: 0.9863 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0958 - accuracy: 0.9852 3072/6993 [============>.................] - ETA: 0s - loss: 0.0938 - accuracy: 0.9854 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0955 - accuracy: 0.9865 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0883 - accuracy: 0.9871 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0848 - accuracy: 0.9866 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0837 - accuracy: 0.9861 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0875 - accuracy: 0.9861 - val_loss: 0.5360 - val_accuracy: 0.9297 Epoch 152/199 128/6993 [..............................] - ETA: 0s - loss: 0.0740 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0941 - accuracy: 0.9788 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0573 - accuracy: 0.9862 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0561 - accuracy: 0.9875 3328/6993 [=============>................] - ETA: 0s - loss: 0.0732 - accuracy: 0.9871 4224/6993 [=================>............] - ETA: 0s - loss: 0.0973 - accuracy: 0.9875 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1011 - accuracy: 0.9867 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0956 - accuracy: 0.9874 6784/6993 [============================>.] - ETA: 0s - loss: 0.0940 - accuracy: 0.9876 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0929 - accuracy: 0.9878 - val_loss: 0.6522 - val_accuracy: 0.9232 Epoch 153/199 128/6993 [..............................] - ETA: 0s - loss: 0.0193 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0886 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0957 - accuracy: 0.9815 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0706 - accuracy: 0.9858 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9868 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0694 - accuracy: 0.9871 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0677 - accuracy: 0.9879 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0760 - accuracy: 0.9859 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0732 - accuracy: 0.9868 6912/6993 [============================>.] - ETA: 0s - loss: 0.0713 - accuracy: 0.9874 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0715 - accuracy: 0.9874 - val_loss: 0.5985 - val_accuracy: 0.9206 Epoch 154/199 128/6993 [..............................] - ETA: 0s - loss: 0.0481 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0668 - accuracy: 0.9870 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1163 - accuracy: 0.9857 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0928 - accuracy: 0.9878 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0773 - accuracy: 0.9885 3328/6993 [=============>................] - ETA: 0s - loss: 0.0636 - accuracy: 0.9907 3968/6993 [================>.............] - ETA: 0s - loss: 0.0718 - accuracy: 0.9894 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0678 - accuracy: 0.9886 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0685 - accuracy: 0.9877 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0792 - accuracy: 0.9870 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0791 - accuracy: 0.9873 - val_loss: 0.5814 - val_accuracy: 0.9262 Epoch 155/199 128/6993 [..............................] - ETA: 0s - loss: 0.0150 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0512 - accuracy: 0.9896 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0517 - accuracy: 0.9898 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0555 - accuracy: 0.9902 3456/6993 [=============>................] - ETA: 0s - loss: 0.0549 - accuracy: 0.9902 4224/6993 [=================>............] - ETA: 0s - loss: 0.0533 - accuracy: 0.9903 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0589 - accuracy: 0.9895 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0669 - accuracy: 0.9885 6784/6993 [============================>.] - ETA: 0s - loss: 0.0678 - accuracy: 0.9882 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0684 - accuracy: 0.9877 - val_loss: 0.7071 - val_accuracy: 0.9232 Epoch 156/199 128/6993 [..............................] - ETA: 0s - loss: 0.1876 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0729 - accuracy: 0.9854 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0632 - accuracy: 0.9894 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0481 - accuracy: 0.9918 3456/6993 [=============>................] - ETA: 0s - loss: 0.0445 - accuracy: 0.9907 4352/6993 [=================>............] - ETA: 0s - loss: 0.0385 - accuracy: 0.9915 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0462 - accuracy: 0.9910 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0540 - accuracy: 0.9902 6912/6993 [============================>.] - ETA: 0s - loss: 0.0542 - accuracy: 0.9896 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0537 - accuracy: 0.9897 - val_loss: 0.6870 - val_accuracy: 0.9262 Epoch 157/199 128/6993 [..............................] - ETA: 0s - loss: 0.0591 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0288 - accuracy: 0.9933 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0386 - accuracy: 0.9916 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0507 - accuracy: 0.9905 3200/6993 [============>.................] - ETA: 0s - loss: 0.0529 - accuracy: 0.9897 3968/6993 [================>.............] - ETA: 0s - loss: 0.0553 - accuracy: 0.9877 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0504 - accuracy: 0.9885 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0487 - accuracy: 0.9892 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0493 - accuracy: 0.9891 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0495 - accuracy: 0.9888 - val_loss: 0.6422 - val_accuracy: 0.9312 Epoch 158/199 128/6993 [..............................] - ETA: 0s - loss: 0.0020 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0551 - accuracy: 0.9870 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0462 - accuracy: 0.9892 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0482 - accuracy: 0.9889 3328/6993 [=============>................] - ETA: 0s - loss: 0.0439 - accuracy: 0.9889 4096/6993 [================>.............] - ETA: 0s - loss: 0.0534 - accuracy: 0.9878 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0580 - accuracy: 0.9884 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0590 - accuracy: 0.9885 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0611 - accuracy: 0.9882 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0638 - accuracy: 0.9881 - val_loss: 0.6334 - val_accuracy: 0.9333 Epoch 159/199 128/6993 [..............................] - ETA: 0s - loss: 0.1334 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1348 - accuracy: 0.9833 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0872 - accuracy: 0.9872 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0868 - accuracy: 0.9877 3456/6993 [=============>................] - ETA: 0s - loss: 0.0811 - accuracy: 0.9873 4352/6993 [=================>............] - ETA: 0s - loss: 0.0731 - accuracy: 0.9874 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0730 - accuracy: 0.9865 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0679 - accuracy: 0.9870 6784/6993 [============================>.] - ETA: 0s - loss: 0.0653 - accuracy: 0.9876 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0642 - accuracy: 0.9878 - val_loss: 0.6735 - val_accuracy: 0.9328 Epoch 160/199 128/6993 [..............................] - ETA: 0s - loss: 0.0199 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0879 - accuracy: 0.9833 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0742 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0891 - accuracy: 0.9875 3456/6993 [=============>................] - ETA: 0s - loss: 0.0774 - accuracy: 0.9893 4224/6993 [=================>............] - ETA: 0s - loss: 0.0783 - accuracy: 0.9891 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0895 - accuracy: 0.9878 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0850 - accuracy: 0.9882 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0810 - accuracy: 0.9875 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0784 - accuracy: 0.9874 - val_loss: 0.6193 - val_accuracy: 0.9358 Epoch 161/199 128/6993 [..............................] - ETA: 0s - loss: 0.0256 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0916 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1059 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0838 - accuracy: 0.9863 3200/6993 [============>.................] - ETA: 0s - loss: 0.0771 - accuracy: 0.9875 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0688 - accuracy: 0.9878 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0773 - accuracy: 0.9866 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0699 - accuracy: 0.9875 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0673 - accuracy: 0.9878 6784/6993 [============================>.] - ETA: 0s - loss: 0.0662 - accuracy: 0.9875 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0646 - accuracy: 0.9876 - val_loss: 0.6741 - val_accuracy: 0.9267 Epoch 162/199 128/6993 [..............................] - ETA: 0s - loss: 0.0694 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0728 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0759 - accuracy: 0.9855 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0717 - accuracy: 0.9863 3328/6993 [=============>................] - ETA: 0s - loss: 0.0738 - accuracy: 0.9859 4224/6993 [=================>............] - ETA: 0s - loss: 0.0703 - accuracy: 0.9872 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0724 - accuracy: 0.9876 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0757 - accuracy: 0.9874 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0736 - accuracy: 0.9880 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0737 - accuracy: 0.9880 - val_loss: 0.6852 - val_accuracy: 0.9277 Epoch 163/199 128/6993 [..............................] - ETA: 0s - loss: 0.0644 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0488 - accuracy: 0.9873 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0624 - accuracy: 0.9862 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0680 - accuracy: 0.9852 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0665 - accuracy: 0.9851 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0692 - accuracy: 0.9849 4224/6993 [=================>............] - ETA: 0s - loss: 0.0809 - accuracy: 0.9841 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0862 - accuracy: 0.9844 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0804 - accuracy: 0.9844 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0791 - accuracy: 0.9839 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0759 - accuracy: 0.9842 6993/6993 [==============================] - 1s 107us/sample - loss: 0.0737 - accuracy: 0.9848 - val_loss: 0.6804 - val_accuracy: 0.9312 Epoch 164/199 128/6993 [..............................] - ETA: 0s - loss: 0.1705 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1158 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0854 - accuracy: 0.9874 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0698 - accuracy: 0.9887 3456/6993 [=============>................] - ETA: 0s - loss: 0.0733 - accuracy: 0.9876 4224/6993 [=================>............] - ETA: 0s - loss: 0.0677 - accuracy: 0.9882 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0665 - accuracy: 0.9881 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0708 - accuracy: 0.9869 6912/6993 [============================>.] - ETA: 0s - loss: 0.0776 - accuracy: 0.9857 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0781 - accuracy: 0.9857 - val_loss: 0.6191 - val_accuracy: 0.9262 Epoch 165/199 128/6993 [..............................] - ETA: 0s - loss: 0.0017 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0677 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0669 - accuracy: 0.9911 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0667 - accuracy: 0.9900 3456/6993 [=============>................] - ETA: 0s - loss: 0.0640 - accuracy: 0.9910 4352/6993 [=================>............] - ETA: 0s - loss: 0.0750 - accuracy: 0.9885 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0738 - accuracy: 0.9872 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0775 - accuracy: 0.9881 6912/6993 [============================>.] - ETA: 0s - loss: 0.0738 - accuracy: 0.9883 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0745 - accuracy: 0.9881 - val_loss: 0.6961 - val_accuracy: 0.9252 Epoch 166/199 128/6993 [..............................] - ETA: 0s - loss: 0.0163 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0376 - accuracy: 0.9922 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0653 - accuracy: 0.9850 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0513 - accuracy: 0.9879 3328/6993 [=============>................] - ETA: 0s - loss: 0.0590 - accuracy: 0.9883 4224/6993 [=================>............] - ETA: 0s - loss: 0.0604 - accuracy: 0.9884 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0610 - accuracy: 0.9881 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0563 - accuracy: 0.9885 6784/6993 [============================>.] - ETA: 0s - loss: 0.0567 - accuracy: 0.9884 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0565 - accuracy: 0.9886 - val_loss: 0.5433 - val_accuracy: 0.9262 Epoch 167/199 128/6993 [..............................] - ETA: 0s - loss: 0.0686 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0668 - accuracy: 0.9814 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0626 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0741 - accuracy: 0.9836 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0987 - accuracy: 0.9824 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0888 - accuracy: 0.9844 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0825 - accuracy: 0.9855 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0857 - accuracy: 0.9850 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0801 - accuracy: 0.9854 - val_loss: 0.6909 - val_accuracy: 0.9312 Epoch 168/199 128/6993 [..............................] - ETA: 0s - loss: 0.0180 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1074 - accuracy: 0.9844 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0987 - accuracy: 0.9854 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0895 - accuracy: 0.9866 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0765 - accuracy: 0.9874 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0829 - accuracy: 0.9871 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0892 - accuracy: 0.9861 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0816 - accuracy: 0.9865 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0876 - accuracy: 0.9864 - val_loss: 0.5521 - val_accuracy: 0.9312 Epoch 169/199 128/6993 [..............................] - ETA: 0s - loss: 0.0633 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0470 - accuracy: 0.9873 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0491 - accuracy: 0.9877 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0446 - accuracy: 0.9888 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0420 - accuracy: 0.9902 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0399 - accuracy: 0.9902 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0505 - accuracy: 0.9894 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0585 - accuracy: 0.9891 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0599 - accuracy: 0.9891 - val_loss: 0.6672 - val_accuracy: 0.9267 Epoch 170/199 128/6993 [..............................] - ETA: 0s - loss: 0.0345 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0301 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0431 - accuracy: 0.9874 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0371 - accuracy: 0.9883 3456/6993 [=============>................] - ETA: 0s - loss: 0.0578 - accuracy: 0.9887 4352/6993 [=================>............] - ETA: 0s - loss: 0.0619 - accuracy: 0.9881 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0625 - accuracy: 0.9876 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0608 - accuracy: 0.9870 6912/6993 [============================>.] - ETA: 0s - loss: 0.0632 - accuracy: 0.9868 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0629 - accuracy: 0.9868 - val_loss: 0.5670 - val_accuracy: 0.9333 Epoch 171/199 128/6993 [..............................] - ETA: 0s - loss: 0.0808 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0887 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0573 - accuracy: 0.9872 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0865 - accuracy: 0.9852 3072/6993 [============>.................] - ETA: 0s - loss: 0.0707 - accuracy: 0.9873 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0666 - accuracy: 0.9875 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0699 - accuracy: 0.9879 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0741 - accuracy: 0.9870 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0757 - accuracy: 0.9869 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0724 - accuracy: 0.9871 - val_loss: 0.5471 - val_accuracy: 0.9292 Epoch 172/199 128/6993 [..............................] - ETA: 0s - loss: 0.0232 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0525 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0531 - accuracy: 0.9877 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0774 - accuracy: 0.9855 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0823 - accuracy: 0.9855 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0717 - accuracy: 0.9871 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0668 - accuracy: 0.9875 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0720 - accuracy: 0.9868 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0703 - accuracy: 0.9864 6912/6993 [============================>.] - ETA: 0s - loss: 0.0698 - accuracy: 0.9867 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0691 - accuracy: 0.9868 - val_loss: 0.5550 - val_accuracy: 0.9262 Epoch 173/199 128/6993 [..............................] - ETA: 0s - loss: 0.0442 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0251 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1372 - accuracy: 0.9872 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1106 - accuracy: 0.9858 3072/6993 [============>.................] - ETA: 0s - loss: 0.0975 - accuracy: 0.9880 3968/6993 [================>.............] - ETA: 0s - loss: 0.1016 - accuracy: 0.9864 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0979 - accuracy: 0.9866 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0981 - accuracy: 0.9868 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0941 - accuracy: 0.9872 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0914 - accuracy: 0.9871 - val_loss: 0.5639 - val_accuracy: 0.9383 Epoch 174/199 128/6993 [..............................] - ETA: 0s - loss: 0.0260 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0831 - accuracy: 0.9893 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0599 - accuracy: 0.9891 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0650 - accuracy: 0.9877 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0716 - accuracy: 0.9849 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0717 - accuracy: 0.9848 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0697 - accuracy: 0.9860 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0647 - accuracy: 0.9871 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0634 - accuracy: 0.9874 - val_loss: 0.6978 - val_accuracy: 0.9343 Epoch 175/199 128/6993 [..............................] - ETA: 0s - loss: 0.0871 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0508 - accuracy: 0.9883 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0414 - accuracy: 0.9894 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0703 - accuracy: 0.9885 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0825 - accuracy: 0.9860 4352/6993 [=================>............] - ETA: 0s - loss: 0.0782 - accuracy: 0.9853 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0805 - accuracy: 0.9855 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0763 - accuracy: 0.9854 6912/6993 [============================>.] - ETA: 0s - loss: 0.0717 - accuracy: 0.9858 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0736 - accuracy: 0.9857 - val_loss: 0.6786 - val_accuracy: 0.9328 Epoch 176/199 128/6993 [..............................] - ETA: 0s - loss: 0.0315 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0777 - accuracy: 0.9922 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0665 - accuracy: 0.9892 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0956 - accuracy: 0.9871 3328/6993 [=============>................] - ETA: 0s - loss: 0.0894 - accuracy: 0.9877 4224/6993 [=================>............] - ETA: 0s - loss: 0.0916 - accuracy: 0.9870 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0831 - accuracy: 0.9873 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0764 - accuracy: 0.9879 6784/6993 [============================>.] - ETA: 0s - loss: 0.0711 - accuracy: 0.9882 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0701 - accuracy: 0.9883 - val_loss: 0.6998 - val_accuracy: 0.9323 Epoch 177/199 128/6993 [..............................] - ETA: 0s - loss: 0.2105 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0494 - accuracy: 0.9900 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0522 - accuracy: 0.9916 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0482 - accuracy: 0.9914 3456/6993 [=============>................] - ETA: 0s - loss: 0.0434 - accuracy: 0.9919 4352/6993 [=================>............] - ETA: 0s - loss: 0.0688 - accuracy: 0.9892 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0717 - accuracy: 0.9891 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0808 - accuracy: 0.9890 6784/6993 [============================>.] - ETA: 0s - loss: 0.0791 - accuracy: 0.9888 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0793 - accuracy: 0.9884 - val_loss: 0.6664 - val_accuracy: 0.9282 Epoch 178/199 128/6993 [..............................] - ETA: 0s - loss: 0.0481 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0868 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0677 - accuracy: 0.9860 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0622 - accuracy: 0.9859 3456/6993 [=============>................] - ETA: 0s - loss: 0.0725 - accuracy: 0.9852 4352/6993 [=================>............] - ETA: 0s - loss: 0.0733 - accuracy: 0.9871 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0772 - accuracy: 0.9854 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0756 - accuracy: 0.9857 6912/6993 [============================>.] - ETA: 0s - loss: 0.0757 - accuracy: 0.9857 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0749 - accuracy: 0.9858 - val_loss: 0.6367 - val_accuracy: 0.9302 Epoch 179/199 128/6993 [..............................] - ETA: 0s - loss: 0.0092 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1321 - accuracy: 0.9932 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0947 - accuracy: 0.9911 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0783 - accuracy: 0.9914 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0841 - accuracy: 0.9883 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0750 - accuracy: 0.9893 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0725 - accuracy: 0.9895 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0731 - accuracy: 0.9892 6784/6993 [============================>.] - ETA: 0s - loss: 0.0715 - accuracy: 0.9886 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0734 - accuracy: 0.9883 - val_loss: 0.7006 - val_accuracy: 0.9242 Epoch 180/199 128/6993 [..............................] - ETA: 0s - loss: 0.0205 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0859 - accuracy: 0.9833 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0732 - accuracy: 0.9850 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0613 - accuracy: 0.9855 3328/6993 [=============>................] - ETA: 0s - loss: 0.0535 - accuracy: 0.9868 4096/6993 [================>.............] - ETA: 0s - loss: 0.0517 - accuracy: 0.9875 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0517 - accuracy: 0.9882 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0567 - accuracy: 0.9889 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0628 - accuracy: 0.9887 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0614 - accuracy: 0.9887 - val_loss: 0.6554 - val_accuracy: 0.9312 Epoch 181/199 128/6993 [..............................] - ETA: 0s - loss: 0.1762 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0618 - accuracy: 0.9854 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0821 - accuracy: 0.9860 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0843 - accuracy: 0.9866 3456/6993 [=============>................] - ETA: 0s - loss: 0.0960 - accuracy: 0.9852 4352/6993 [=================>............] - ETA: 0s - loss: 0.0923 - accuracy: 0.9867 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1040 - accuracy: 0.9865 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1100 - accuracy: 0.9861 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1010 - accuracy: 0.9863 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1002 - accuracy: 0.9861 - val_loss: 0.5343 - val_accuracy: 0.9353 Epoch 182/199 128/6993 [..............................] - ETA: 0s - loss: 0.0578 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0562 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0564 - accuracy: 0.9851 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9839 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0705 - accuracy: 0.9840 3200/6993 [============>.................] - ETA: 0s - loss: 0.0639 - accuracy: 0.9853 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0575 - accuracy: 0.9857 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0550 - accuracy: 0.9862 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0527 - accuracy: 0.9867 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0498 - accuracy: 0.9874 6784/6993 [============================>.] - ETA: 0s - loss: 0.0540 - accuracy: 0.9878 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0570 - accuracy: 0.9878 - val_loss: 0.6003 - val_accuracy: 0.9282 Epoch 183/199 128/6993 [..............................] - ETA: 0s - loss: 0.0307 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0804 - accuracy: 0.9831 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0581 - accuracy: 0.9870 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0449 - accuracy: 0.9894 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0478 - accuracy: 0.9892 3328/6993 [=============>................] - ETA: 0s - loss: 0.0430 - accuracy: 0.9898 4096/6993 [================>.............] - ETA: 0s - loss: 0.0444 - accuracy: 0.9895 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0482 - accuracy: 0.9896 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0626 - accuracy: 0.9886 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0636 - accuracy: 0.9886 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0611 - accuracy: 0.9888 - val_loss: 0.6206 - val_accuracy: 0.9257 Epoch 184/199 128/6993 [..............................] - ETA: 0s - loss: 0.1339 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0960 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0761 - accuracy: 0.9877 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0701 - accuracy: 0.9879 3456/6993 [=============>................] - ETA: 0s - loss: 0.0613 - accuracy: 0.9884 4224/6993 [=================>............] - ETA: 0s - loss: 0.0563 - accuracy: 0.9886 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0581 - accuracy: 0.9878 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0618 - accuracy: 0.9878 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0558 - accuracy: 0.9891 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0554 - accuracy: 0.9891 - val_loss: 0.6333 - val_accuracy: 0.9287 Epoch 185/199 128/6993 [..............................] - ETA: 0s - loss: 0.0931 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0370 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0480 - accuracy: 0.9892 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0974 - accuracy: 0.9860 3200/6993 [============>.................] - ETA: 0s - loss: 0.0871 - accuracy: 0.9869 4096/6993 [================>.............] - ETA: 0s - loss: 0.0844 - accuracy: 0.9868 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0839 - accuracy: 0.9860 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0843 - accuracy: 0.9862 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0844 - accuracy: 0.9865 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0826 - accuracy: 0.9866 - val_loss: 0.6363 - val_accuracy: 0.9307 Epoch 186/199 128/6993 [..............................] - ETA: 0s - loss: 0.3661 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0996 - accuracy: 0.9855 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0788 - accuracy: 0.9868 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0753 - accuracy: 0.9881 3200/6993 [============>.................] - ETA: 0s - loss: 0.0673 - accuracy: 0.9878 3968/6993 [================>.............] - ETA: 0s - loss: 0.0604 - accuracy: 0.9884 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0623 - accuracy: 0.9882 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0621 - accuracy: 0.9876 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0619 - accuracy: 0.9877 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0669 - accuracy: 0.9884 - val_loss: 0.6295 - val_accuracy: 0.9312 Epoch 187/199 128/6993 [..............................] - ETA: 0s - loss: 0.0761 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0274 - accuracy: 0.9912 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0715 - accuracy: 0.9900 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0549 - accuracy: 0.9911 3456/6993 [=============>................] - ETA: 0s - loss: 0.0573 - accuracy: 0.9896 4224/6993 [=================>............] - ETA: 0s - loss: 0.0528 - accuracy: 0.9898 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0549 - accuracy: 0.9898 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0562 - accuracy: 0.9893 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0688 - accuracy: 0.9886 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0700 - accuracy: 0.9881 - val_loss: 0.6381 - val_accuracy: 0.9262 Epoch 188/199 128/6993 [..............................] - ETA: 0s - loss: 0.0856 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0637 - accuracy: 0.9873 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0623 - accuracy: 0.9865 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0763 - accuracy: 0.9851 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0682 - accuracy: 0.9860 4352/6993 [=================>............] - ETA: 0s - loss: 0.0766 - accuracy: 0.9853 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0702 - accuracy: 0.9865 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0751 - accuracy: 0.9862 6912/6993 [============================>.] - ETA: 0s - loss: 0.0696 - accuracy: 0.9867 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0688 - accuracy: 0.9868 - val_loss: 0.5958 - val_accuracy: 0.9312 Epoch 189/199 128/6993 [..............................] - ETA: 0s - loss: 0.1635 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0887 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0636 - accuracy: 0.9888 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0844 - accuracy: 0.9875 3456/6993 [=============>................] - ETA: 0s - loss: 0.0751 - accuracy: 0.9878 4352/6993 [=================>............] - ETA: 0s - loss: 0.0742 - accuracy: 0.9876 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0770 - accuracy: 0.9869 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0713 - accuracy: 0.9875 6784/6993 [============================>.] - ETA: 0s - loss: 0.0693 - accuracy: 0.9878 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0692 - accuracy: 0.9877 - val_loss: 0.5804 - val_accuracy: 0.9277 Epoch 190/199 128/6993 [..............................] - ETA: 0s - loss: 0.0066 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0591 - accuracy: 0.9834 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0732 - accuracy: 0.9849 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0787 - accuracy: 0.9874 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0718 - accuracy: 0.9880 4352/6993 [=================>............] - ETA: 0s - loss: 0.0695 - accuracy: 0.9876 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0703 - accuracy: 0.9867 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0720 - accuracy: 0.9868 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0723 - accuracy: 0.9870 - val_loss: 0.5470 - val_accuracy: 0.9368 Epoch 191/199 128/6993 [..............................] - ETA: 0s - loss: 0.0336 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0338 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0367 - accuracy: 0.9911 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0493 - accuracy: 0.9905 3072/6993 [============>.................] - ETA: 0s - loss: 0.0468 - accuracy: 0.9906 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0533 - accuracy: 0.9898 4224/6993 [=================>............] - ETA: 0s - loss: 0.0622 - accuracy: 0.9896 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0683 - accuracy: 0.9901 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0680 - accuracy: 0.9895 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0697 - accuracy: 0.9893 6912/6993 [============================>.] - ETA: 0s - loss: 0.0735 - accuracy: 0.9887 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0755 - accuracy: 0.9884 - val_loss: 0.6436 - val_accuracy: 0.9312 Epoch 192/199 128/6993 [..............................] - ETA: 0s - loss: 0.0045 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1103 - accuracy: 0.9844 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0770 - accuracy: 0.9859 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0748 - accuracy: 0.9858 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0713 - accuracy: 0.9855 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0694 - accuracy: 0.9868 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0677 - accuracy: 0.9872 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0635 - accuracy: 0.9875 6784/6993 [============================>.] - ETA: 0s - loss: 0.0675 - accuracy: 0.9870 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0675 - accuracy: 0.9871 - val_loss: 0.6712 - val_accuracy: 0.9282 Epoch 193/199 128/6993 [..............................] - ETA: 0s - loss: 0.0268 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0430 - accuracy: 0.9909 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0485 - accuracy: 0.9889 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0372 - accuracy: 0.9901 3328/6993 [=============>................] - ETA: 0s - loss: 0.0388 - accuracy: 0.9907 4096/6993 [================>.............] - ETA: 0s - loss: 0.0401 - accuracy: 0.9902 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0386 - accuracy: 0.9910 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0577 - accuracy: 0.9910 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0561 - accuracy: 0.9905 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0539 - accuracy: 0.9908 - val_loss: 0.7440 - val_accuracy: 0.9302 Epoch 194/199 128/6993 [..............................] - ETA: 0s - loss: 0.0291 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0568 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0431 - accuracy: 0.9911 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0637 - accuracy: 0.9914 3456/6993 [=============>................] - ETA: 0s - loss: 0.0608 - accuracy: 0.9916 4352/6993 [=================>............] - ETA: 0s - loss: 0.0659 - accuracy: 0.9910 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0722 - accuracy: 0.9905 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0832 - accuracy: 0.9899 6912/6993 [============================>.] - ETA: 0s - loss: 0.0926 - accuracy: 0.9900 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0918 - accuracy: 0.9900 - val_loss: 0.6474 - val_accuracy: 0.9338 Epoch 195/199 128/6993 [..............................] - ETA: 0s - loss: 0.0149 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0681 - accuracy: 0.9821 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0603 - accuracy: 0.9850 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0794 - accuracy: 0.9865 3072/6993 [============>.................] - ETA: 0s - loss: 0.0721 - accuracy: 0.9863 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0689 - accuracy: 0.9870 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0649 - accuracy: 0.9874 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0633 - accuracy: 0.9876 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0783 - accuracy: 0.9872 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0830 - accuracy: 0.9868 - val_loss: 0.6191 - val_accuracy: 0.9302 Epoch 196/199 128/6993 [..............................] - ETA: 0s - loss: 0.0061 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0295 - accuracy: 0.9933 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0479 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0455 - accuracy: 0.9907 3328/6993 [=============>................] - ETA: 0s - loss: 0.0520 - accuracy: 0.9904 3968/6993 [================>.............] - ETA: 0s - loss: 0.0555 - accuracy: 0.9899 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0607 - accuracy: 0.9892 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0684 - accuracy: 0.9886 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0671 - accuracy: 0.9882 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0702 - accuracy: 0.9873 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0678 - accuracy: 0.9877 - val_loss: 0.6900 - val_accuracy: 0.9262 Epoch 197/199 128/6993 [..............................] - ETA: 0s - loss: 0.0192 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0309 - accuracy: 0.9900 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0521 - accuracy: 0.9872 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0666 - accuracy: 0.9879 3456/6993 [=============>................] - ETA: 0s - loss: 0.0640 - accuracy: 0.9878 4224/6993 [=================>............] - ETA: 0s - loss: 0.0662 - accuracy: 0.9882 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0677 - accuracy: 0.9872 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0684 - accuracy: 0.9869 6784/6993 [============================>.] - ETA: 0s - loss: 0.0670 - accuracy: 0.9866 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0730 - accuracy: 0.9863 - val_loss: 0.6282 - val_accuracy: 0.9287 Epoch 198/199 128/6993 [..............................] - ETA: 0s - loss: 0.1742 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0948 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0748 - accuracy: 0.9865 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0713 - accuracy: 0.9877 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0748 - accuracy: 0.9871 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0733 - accuracy: 0.9885 3328/6993 [=============>................] - ETA: 0s - loss: 0.0751 - accuracy: 0.9883 3968/6993 [================>.............] - ETA: 0s - loss: 0.0720 - accuracy: 0.9887 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0738 - accuracy: 0.9876 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0759 - accuracy: 0.9880 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0783 - accuracy: 0.9885 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0777 - accuracy: 0.9882 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0788 - accuracy: 0.9886 - val_loss: 0.6019 - val_accuracy: 0.9338 Epoch 199/199 128/6993 [..............................] - ETA: 1s - loss: 0.1042 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0667 - accuracy: 0.9912 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0577 - accuracy: 0.9911 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0616 - accuracy: 0.9891 3200/6993 [============>.................] - ETA: 0s - loss: 0.0583 - accuracy: 0.9887 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0668 - accuracy: 0.9871 4352/6993 [=================>............] - ETA: 0s - loss: 0.0781 - accuracy: 0.9862 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0704 - accuracy: 0.9876 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0690 - accuracy: 0.9877 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0707 - accuracy: 0.9870 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0693 - accuracy: 0.9874 - val_loss: 0.7114 - val_accuracy: 0.9282 Evaluating model for iteration 0... 1019/1019 - 0s - loss: 0.7889 - accuracy: 0.9264 Accuracy for iteration 0 0.9263984560966492 Training model for iteration 1... Train on 6993 samples, validate on 1978 samples Epoch 1/199 128/6993 [..............................] - ETA: 17s - loss: 2.3209 - accuracy: 0.0703 896/6993 [==>...........................] - ETA: 2s - loss: 2.1926 - accuracy: 0.1897 1664/6993 [======>.......................] - ETA: 1s - loss: 2.0783 - accuracy: 0.2356 2432/6993 [=========>....................] - ETA: 0s - loss: 1.9828 - accuracy: 0.2780 3200/6993 [============>.................] - ETA: 0s - loss: 1.9093 - accuracy: 0.3069 3968/6993 [================>.............] - ETA: 0s - loss: 1.8708 - accuracy: 0.3191 4864/6993 [===================>..........] - ETA: 0s - loss: 1.8135 - accuracy: 0.3427 5504/6993 [======================>.......] - ETA: 0s - loss: 1.7754 - accuracy: 0.3552 6272/6993 [=========================>....] - ETA: 0s - loss: 1.7418 - accuracy: 0.3667 6912/6993 [============================>.] - ETA: 0s - loss: 1.7151 - accuracy: 0.3791 6993/6993 [==============================] - 1s 173us/sample - loss: 1.7141 - accuracy: 0.3792 - val_loss: 1.2289 - val_accuracy: 0.5885 Epoch 2/199 128/6993 [..............................] - ETA: 0s - loss: 1.3682 - accuracy: 0.5078 1024/6993 [===>..........................] - ETA: 0s - loss: 1.3506 - accuracy: 0.5293 1792/6993 [======>.......................] - ETA: 0s - loss: 1.3280 - accuracy: 0.5424 2688/6993 [==========>...................] - ETA: 0s - loss: 1.3211 - accuracy: 0.5506 3456/6993 [=============>................] - ETA: 0s - loss: 1.3062 - accuracy: 0.5538 4352/6993 [=================>............] - ETA: 0s - loss: 1.2910 - accuracy: 0.5616 5120/6993 [====================>.........] - ETA: 0s - loss: 1.2693 - accuracy: 0.5701 6016/6993 [========================>.....] - ETA: 0s - loss: 1.2577 - accuracy: 0.5721 6912/6993 [============================>.] - ETA: 0s - loss: 1.2460 - accuracy: 0.5752 6993/6993 [==============================] - 1s 81us/sample - loss: 1.2419 - accuracy: 0.5760 - val_loss: 0.9635 - val_accuracy: 0.6663 Epoch 3/199 128/6993 [..............................] - ETA: 0s - loss: 1.1477 - accuracy: 0.6016 1024/6993 [===>..........................] - ETA: 0s - loss: 1.1343 - accuracy: 0.6230 1920/6993 [=======>......................] - ETA: 0s - loss: 1.1122 - accuracy: 0.6328 2816/6993 [===========>..................] - ETA: 0s - loss: 1.0844 - accuracy: 0.6424 3584/6993 [==============>...............] - ETA: 0s - loss: 1.0642 - accuracy: 0.6443 4224/6993 [=================>............] - ETA: 0s - loss: 1.0594 - accuracy: 0.6468 5120/6993 [====================>.........] - ETA: 0s - loss: 1.0415 - accuracy: 0.6486 6016/6993 [========================>.....] - ETA: 0s - loss: 1.0286 - accuracy: 0.6541 6784/6993 [============================>.] - ETA: 0s - loss: 1.0137 - accuracy: 0.6592 6993/6993 [==============================] - 1s 78us/sample - loss: 1.0176 - accuracy: 0.6569 - val_loss: 0.8463 - val_accuracy: 0.7123 Epoch 4/199 128/6993 [..............................] - ETA: 0s - loss: 0.7844 - accuracy: 0.7656 896/6993 [==>...........................] - ETA: 0s - loss: 0.8854 - accuracy: 0.7065 1792/6993 [======>.......................] - ETA: 0s - loss: 0.8720 - accuracy: 0.7182 2560/6993 [=========>....................] - ETA: 0s - loss: 0.8851 - accuracy: 0.7109 3456/6993 [=============>................] - ETA: 0s - loss: 0.8943 - accuracy: 0.7031 4224/6993 [=================>............] - ETA: 0s - loss: 0.8883 - accuracy: 0.7071 5120/6993 [====================>.........] - ETA: 0s - loss: 0.9032 - accuracy: 0.7064 6016/6993 [========================>.....] - ETA: 0s - loss: 0.8962 - accuracy: 0.7071 6784/6993 [============================>.] - ETA: 0s - loss: 0.8874 - accuracy: 0.7099 6993/6993 [==============================] - 1s 78us/sample - loss: 0.8889 - accuracy: 0.7101 - val_loss: 0.7244 - val_accuracy: 0.7513 Epoch 5/199 128/6993 [..............................] - ETA: 0s - loss: 0.8617 - accuracy: 0.7344 896/6993 [==>...........................] - ETA: 0s - loss: 0.8227 - accuracy: 0.7422 1792/6993 [======>.......................] - ETA: 0s - loss: 0.8158 - accuracy: 0.7360 2688/6993 [==========>...................] - ETA: 0s - loss: 0.7969 - accuracy: 0.7433 3328/6993 [=============>................] - ETA: 0s - loss: 0.7891 - accuracy: 0.7446 4096/6993 [================>.............] - ETA: 0s - loss: 0.7831 - accuracy: 0.7454 4992/6993 [====================>.........] - ETA: 0s - loss: 0.7865 - accuracy: 0.7448 5888/6993 [========================>.....] - ETA: 0s - loss: 0.7701 - accuracy: 0.7458 6656/6993 [===========================>..] - ETA: 0s - loss: 0.7655 - accuracy: 0.7491 6993/6993 [==============================] - 1s 81us/sample - loss: 0.7700 - accuracy: 0.7473 - val_loss: 0.6921 - val_accuracy: 0.7674 Epoch 6/199 128/6993 [..............................] - ETA: 0s - loss: 0.8257 - accuracy: 0.7109 1024/6993 [===>..........................] - ETA: 0s - loss: 0.6668 - accuracy: 0.7803 1920/6993 [=======>......................] - ETA: 0s - loss: 0.6759 - accuracy: 0.7703 2816/6993 [===========>..................] - ETA: 0s - loss: 0.6946 - accuracy: 0.7692 3584/6993 [==============>...............] - ETA: 0s - loss: 0.6976 - accuracy: 0.7681 4480/6993 [==================>...........] - ETA: 0s - loss: 0.7164 - accuracy: 0.7641 5248/6993 [=====================>........] - ETA: 0s - loss: 0.7130 - accuracy: 0.7668 6144/6993 [=========================>....] - ETA: 0s - loss: 0.7094 - accuracy: 0.7695 6993/6993 [==============================] - 1s 81us/sample - loss: 0.7080 - accuracy: 0.7709 - val_loss: 0.6216 - val_accuracy: 0.7952 Epoch 7/199 128/6993 [..............................] - ETA: 0s - loss: 0.7292 - accuracy: 0.7422 1024/6993 [===>..........................] - ETA: 0s - loss: 0.6223 - accuracy: 0.7969 1920/6993 [=======>......................] - ETA: 0s - loss: 0.6226 - accuracy: 0.7974 2560/6993 [=========>....................] - ETA: 0s - loss: 0.6291 - accuracy: 0.7984 3456/6993 [=============>................] - ETA: 0s - loss: 0.6511 - accuracy: 0.7873 4224/6993 [=================>............] - ETA: 0s - loss: 0.6458 - accuracy: 0.7888 5120/6993 [====================>.........] - ETA: 0s - loss: 0.6501 - accuracy: 0.7891 6016/6993 [========================>.....] - ETA: 0s - loss: 0.6396 - accuracy: 0.7907 6784/6993 [============================>.] - ETA: 0s - loss: 0.6269 - accuracy: 0.7960 6993/6993 [==============================] - 1s 79us/sample - loss: 0.6287 - accuracy: 0.7957 - val_loss: 0.5958 - val_accuracy: 0.8028 Epoch 8/199 128/6993 [..............................] - ETA: 0s - loss: 0.5814 - accuracy: 0.8047 1024/6993 [===>..........................] - ETA: 0s - loss: 0.5753 - accuracy: 0.8096 1920/6993 [=======>......................] - ETA: 0s - loss: 0.5932 - accuracy: 0.8047 2560/6993 [=========>....................] - ETA: 0s - loss: 0.5875 - accuracy: 0.8059 3328/6993 [=============>................] - ETA: 0s - loss: 0.5793 - accuracy: 0.8110 4224/6993 [=================>............] - ETA: 0s - loss: 0.5751 - accuracy: 0.8127 5120/6993 [====================>.........] - ETA: 0s - loss: 0.5795 - accuracy: 0.8113 5888/6993 [========================>.....] - ETA: 0s - loss: 0.5700 - accuracy: 0.8154 6784/6993 [============================>.] - ETA: 0s - loss: 0.5780 - accuracy: 0.8129 6993/6993 [==============================] - 1s 81us/sample - loss: 0.5757 - accuracy: 0.8131 - val_loss: 0.6583 - val_accuracy: 0.7791 Epoch 9/199 128/6993 [..............................] - ETA: 0s - loss: 0.7649 - accuracy: 0.7578 768/6993 [==>...........................] - ETA: 0s - loss: 0.5036 - accuracy: 0.8372 1536/6993 [=====>........................] - ETA: 0s - loss: 0.5258 - accuracy: 0.8262 2304/6993 [========>.....................] - ETA: 0s - loss: 0.5008 - accuracy: 0.8385 3072/6993 [============>.................] - ETA: 0s - loss: 0.4987 - accuracy: 0.8389 3968/6993 [================>.............] - ETA: 0s - loss: 0.5271 - accuracy: 0.8327 4864/6993 [===================>..........] - ETA: 0s - loss: 0.5248 - accuracy: 0.8353 5632/6993 [=======================>......] - ETA: 0s - loss: 0.5214 - accuracy: 0.8347 6528/6993 [===========================>..] - ETA: 0s - loss: 0.5179 - accuracy: 0.8352 6993/6993 [==============================] - 1s 80us/sample - loss: 0.5190 - accuracy: 0.8348 - val_loss: 0.4991 - val_accuracy: 0.8337 Epoch 10/199 128/6993 [..............................] - ETA: 0s - loss: 0.4129 - accuracy: 0.8516 768/6993 [==>...........................] - ETA: 0s - loss: 0.4150 - accuracy: 0.8698 1408/6993 [=====>........................] - ETA: 0s - loss: 0.4664 - accuracy: 0.8622 2304/6993 [========>.....................] - ETA: 0s - loss: 0.4614 - accuracy: 0.8615 3200/6993 [============>.................] - ETA: 0s - loss: 0.4663 - accuracy: 0.8606 4096/6993 [================>.............] - ETA: 0s - loss: 0.4652 - accuracy: 0.8567 4864/6993 [===================>..........] - ETA: 0s - loss: 0.4677 - accuracy: 0.8542 5504/6993 [======================>.......] - ETA: 0s - loss: 0.4682 - accuracy: 0.8543 6144/6993 [=========================>....] - ETA: 0s - loss: 0.4659 - accuracy: 0.8551 6784/6993 [============================>.] - ETA: 0s - loss: 0.4715 - accuracy: 0.8533 6993/6993 [==============================] - 1s 92us/sample - loss: 0.4785 - accuracy: 0.8520 - val_loss: 0.5207 - val_accuracy: 0.8367 Epoch 11/199 128/6993 [..............................] - ETA: 0s - loss: 0.3764 - accuracy: 0.8516 768/6993 [==>...........................] - ETA: 0s - loss: 0.3808 - accuracy: 0.8802 1408/6993 [=====>........................] - ETA: 0s - loss: 0.3888 - accuracy: 0.8906 2176/6993 [========>.....................] - ETA: 0s - loss: 0.3784 - accuracy: 0.8883 3072/6993 [============>.................] - ETA: 0s - loss: 0.3772 - accuracy: 0.8844 3968/6993 [================>.............] - ETA: 0s - loss: 0.3923 - accuracy: 0.8778 4864/6993 [===================>..........] - ETA: 0s - loss: 0.4043 - accuracy: 0.8723 5760/6993 [=======================>......] - ETA: 0s - loss: 0.4137 - accuracy: 0.8691 6528/6993 [===========================>..] - ETA: 0s - loss: 0.4203 - accuracy: 0.8681 6993/6993 [==============================] - 1s 83us/sample - loss: 0.4212 - accuracy: 0.8690 - val_loss: 0.5257 - val_accuracy: 0.8438 Epoch 12/199 128/6993 [..............................] - ETA: 0s - loss: 0.3648 - accuracy: 0.8672 896/6993 [==>...........................] - ETA: 0s - loss: 0.3986 - accuracy: 0.8772 1792/6993 [======>.......................] - ETA: 0s - loss: 0.3910 - accuracy: 0.8850 2688/6993 [==========>...................] - ETA: 0s - loss: 0.3950 - accuracy: 0.8839 3456/6993 [=============>................] - ETA: 0s - loss: 0.4039 - accuracy: 0.8811 4352/6993 [=================>............] - ETA: 0s - loss: 0.3895 - accuracy: 0.8842 5248/6993 [=====================>........] - ETA: 0s - loss: 0.3913 - accuracy: 0.8832 6144/6993 [=========================>....] - ETA: 0s - loss: 0.3947 - accuracy: 0.8812 6784/6993 [============================>.] - ETA: 0s - loss: 0.3999 - accuracy: 0.8788 6993/6993 [==============================] - 1s 76us/sample - loss: 0.4036 - accuracy: 0.8784 - val_loss: 0.5535 - val_accuracy: 0.8286 Epoch 13/199 128/6993 [..............................] - ETA: 0s - loss: 0.5413 - accuracy: 0.8516 896/6993 [==>...........................] - ETA: 0s - loss: 0.3878 - accuracy: 0.8717 1792/6993 [======>.......................] - ETA: 0s - loss: 0.3394 - accuracy: 0.8873 2688/6993 [==========>...................] - ETA: 0s - loss: 0.3631 - accuracy: 0.8854 3456/6993 [=============>................] - ETA: 0s - loss: 0.3422 - accuracy: 0.8909 4352/6993 [=================>............] - ETA: 0s - loss: 0.3521 - accuracy: 0.8890 5248/6993 [=====================>........] - ETA: 0s - loss: 0.3493 - accuracy: 0.8881 6144/6993 [=========================>....] - ETA: 0s - loss: 0.3493 - accuracy: 0.8892 6912/6993 [============================>.] - ETA: 0s - loss: 0.3554 - accuracy: 0.8895 6993/6993 [==============================] - 1s 82us/sample - loss: 0.3563 - accuracy: 0.8893 - val_loss: 0.4122 - val_accuracy: 0.8802 Epoch 14/199 128/6993 [..............................] - ETA: 0s - loss: 0.4172 - accuracy: 0.8672 768/6993 [==>...........................] - ETA: 0s - loss: 0.3997 - accuracy: 0.8776 1408/6993 [=====>........................] - ETA: 0s - loss: 0.3458 - accuracy: 0.8920 2304/6993 [========>.....................] - ETA: 0s - loss: 0.3369 - accuracy: 0.8924 3200/6993 [============>.................] - ETA: 0s - loss: 0.3397 - accuracy: 0.8916 4096/6993 [================>.............] - ETA: 0s - loss: 0.3358 - accuracy: 0.8955 4864/6993 [===================>..........] - ETA: 0s - loss: 0.3431 - accuracy: 0.8931 5504/6993 [======================>.......] - ETA: 0s - loss: 0.3416 - accuracy: 0.8937 6272/6993 [=========================>....] - ETA: 0s - loss: 0.3398 - accuracy: 0.8941 6993/6993 [==============================] - 1s 80us/sample - loss: 0.3356 - accuracy: 0.8955 - val_loss: 0.4617 - val_accuracy: 0.8620 Epoch 15/199 128/6993 [..............................] - ETA: 0s - loss: 0.3095 - accuracy: 0.8828 896/6993 [==>...........................] - ETA: 0s - loss: 0.2694 - accuracy: 0.9107 1792/6993 [======>.......................] - ETA: 0s - loss: 0.2930 - accuracy: 0.9046 2688/6993 [==========>...................] - ETA: 0s - loss: 0.3129 - accuracy: 0.9040 3584/6993 [==============>...............] - ETA: 0s - loss: 0.3083 - accuracy: 0.9060 4352/6993 [=================>............] - ETA: 0s - loss: 0.3004 - accuracy: 0.9079 5248/6993 [=====================>........] - ETA: 0s - loss: 0.3073 - accuracy: 0.9053 6016/6993 [========================>.....] - ETA: 0s - loss: 0.3114 - accuracy: 0.9033 6912/6993 [============================>.] - ETA: 0s - loss: 0.3082 - accuracy: 0.9055 6993/6993 [==============================] - 1s 77us/sample - loss: 0.3080 - accuracy: 0.9052 - val_loss: 0.4995 - val_accuracy: 0.8589 Epoch 16/199 128/6993 [..............................] - ETA: 0s - loss: 0.2808 - accuracy: 0.9141 896/6993 [==>...........................] - ETA: 0s - loss: 0.3542 - accuracy: 0.8895 1792/6993 [======>.......................] - ETA: 0s - loss: 0.3460 - accuracy: 0.8979 2688/6993 [==========>...................] - ETA: 0s - loss: 0.3125 - accuracy: 0.9066 3456/6993 [=============>................] - ETA: 0s - loss: 0.3111 - accuracy: 0.9048 4352/6993 [=================>............] - ETA: 0s - loss: 0.3061 - accuracy: 0.9081 4992/6993 [====================>.........] - ETA: 0s - loss: 0.3080 - accuracy: 0.9069 5760/6993 [=======================>......] - ETA: 0s - loss: 0.3152 - accuracy: 0.9069 6656/6993 [===========================>..] - ETA: 0s - loss: 0.3109 - accuracy: 0.9082 6993/6993 [==============================] - 1s 78us/sample - loss: 0.3077 - accuracy: 0.9091 - val_loss: 0.4180 - val_accuracy: 0.8852 Epoch 17/199 128/6993 [..............................] - ETA: 0s - loss: 0.2657 - accuracy: 0.9219 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2454 - accuracy: 0.9170 1920/6993 [=======>......................] - ETA: 0s - loss: 0.2709 - accuracy: 0.9161 2688/6993 [==========>...................] - ETA: 0s - loss: 0.2729 - accuracy: 0.9156 3584/6993 [==============>...............] - ETA: 0s - loss: 0.2657 - accuracy: 0.9202 4480/6993 [==================>...........] - ETA: 0s - loss: 0.2682 - accuracy: 0.9210 5248/6993 [=====================>........] - ETA: 0s - loss: 0.2678 - accuracy: 0.9205 6016/6993 [========================>.....] - ETA: 0s - loss: 0.2696 - accuracy: 0.9199 6912/6993 [============================>.] - ETA: 0s - loss: 0.2682 - accuracy: 0.9201 6993/6993 [==============================] - 1s 78us/sample - loss: 0.2678 - accuracy: 0.9203 - val_loss: 0.4269 - val_accuracy: 0.8832 Epoch 18/199 128/6993 [..............................] - ETA: 0s - loss: 0.2487 - accuracy: 0.9453 896/6993 [==>...........................] - ETA: 0s - loss: 0.2108 - accuracy: 0.9431 1792/6993 [======>.......................] - ETA: 0s - loss: 0.2323 - accuracy: 0.9392 2560/6993 [=========>....................] - ETA: 0s - loss: 0.2404 - accuracy: 0.9328 3456/6993 [=============>................] - ETA: 0s - loss: 0.2498 - accuracy: 0.9294 4352/6993 [=================>............] - ETA: 0s - loss: 0.2487 - accuracy: 0.9292 4992/6993 [====================>.........] - ETA: 0s - loss: 0.2544 - accuracy: 0.9269 5888/6993 [========================>.....] - ETA: 0s - loss: 0.2572 - accuracy: 0.9236 6656/6993 [===========================>..] - ETA: 0s - loss: 0.2550 - accuracy: 0.9249 6993/6993 [==============================] - 1s 78us/sample - loss: 0.2611 - accuracy: 0.9239 - val_loss: 0.4340 - val_accuracy: 0.8857 Epoch 19/199 128/6993 [..............................] - ETA: 0s - loss: 0.2345 - accuracy: 0.9141 896/6993 [==>...........................] - ETA: 0s - loss: 0.2151 - accuracy: 0.9319 1792/6993 [======>.......................] - ETA: 0s - loss: 0.2306 - accuracy: 0.9269 2688/6993 [==========>...................] - ETA: 0s - loss: 0.2460 - accuracy: 0.9282 3456/6993 [=============>................] - ETA: 0s - loss: 0.2534 - accuracy: 0.9253 4352/6993 [=================>............] - ETA: 0s - loss: 0.2490 - accuracy: 0.9260 5248/6993 [=====================>........] - ETA: 0s - loss: 0.2425 - accuracy: 0.9259 6144/6993 [=========================>....] - ETA: 0s - loss: 0.2469 - accuracy: 0.9237 6993/6993 [==============================] - 1s 78us/sample - loss: 0.2539 - accuracy: 0.9225 - val_loss: 0.3688 - val_accuracy: 0.8984 Epoch 20/199 128/6993 [..............................] - ETA: 0s - loss: 0.2102 - accuracy: 0.9453 896/6993 [==>...........................] - ETA: 0s - loss: 0.3022 - accuracy: 0.9185 1792/6993 [======>.......................] - ETA: 0s - loss: 0.2594 - accuracy: 0.9275 2432/6993 [=========>....................] - ETA: 0s - loss: 0.2452 - accuracy: 0.9330 3072/6993 [============>.................] - ETA: 0s - loss: 0.2353 - accuracy: 0.9365 3456/6993 [=============>................] - ETA: 0s - loss: 0.2336 - accuracy: 0.9361 4096/6993 [================>.............] - ETA: 0s - loss: 0.2282 - accuracy: 0.9363 4736/6993 [===================>..........] - ETA: 0s - loss: 0.2314 - accuracy: 0.9352 5248/6993 [=====================>........] - ETA: 0s - loss: 0.2297 - accuracy: 0.9352 5760/6993 [=======================>......] - ETA: 0s - loss: 0.2322 - accuracy: 0.9345 6272/6993 [=========================>....] - ETA: 0s - loss: 0.2398 - accuracy: 0.9332 6912/6993 [============================>.] - ETA: 0s - loss: 0.2417 - accuracy: 0.9333 6993/6993 [==============================] - 1s 103us/sample - loss: 0.2401 - accuracy: 0.9338 - val_loss: 0.3632 - val_accuracy: 0.8964 Epoch 21/199 128/6993 [..............................] - ETA: 0s - loss: 0.1198 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1505 - accuracy: 0.9531 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1758 - accuracy: 0.9486 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1876 - accuracy: 0.9445 3200/6993 [============>.................] - ETA: 0s - loss: 0.1935 - accuracy: 0.9434 3968/6993 [================>.............] - ETA: 0s - loss: 0.2100 - accuracy: 0.9388 4608/6993 [==================>...........] - ETA: 0s - loss: 0.2083 - accuracy: 0.9397 5376/6993 [======================>.......] - ETA: 0s - loss: 0.2108 - accuracy: 0.9381 6144/6993 [=========================>....] - ETA: 0s - loss: 0.2216 - accuracy: 0.9347 6993/6993 [==============================] - 1s 86us/sample - loss: 0.2173 - accuracy: 0.9345 - val_loss: 0.3604 - val_accuracy: 0.8994 Epoch 22/199 128/6993 [..............................] - ETA: 0s - loss: 0.2228 - accuracy: 0.9141 896/6993 [==>...........................] - ETA: 0s - loss: 0.1958 - accuracy: 0.9353 1792/6993 [======>.......................] - ETA: 0s - loss: 0.2055 - accuracy: 0.9381 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1829 - accuracy: 0.9438 3456/6993 [=============>................] - ETA: 0s - loss: 0.1777 - accuracy: 0.9456 4352/6993 [=================>............] - ETA: 0s - loss: 0.1865 - accuracy: 0.9446 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1909 - accuracy: 0.9443 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1941 - accuracy: 0.9441 6784/6993 [============================>.] - ETA: 0s - loss: 0.1969 - accuracy: 0.9432 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1956 - accuracy: 0.9434 - val_loss: 0.4886 - val_accuracy: 0.8751 Epoch 23/199 128/6993 [..............................] - ETA: 0s - loss: 0.1781 - accuracy: 0.9297 896/6993 [==>...........................] - ETA: 0s - loss: 0.1897 - accuracy: 0.9464 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1970 - accuracy: 0.9465 2304/6993 [========>.....................] - ETA: 0s - loss: 0.2094 - accuracy: 0.9405 3072/6993 [============>.................] - ETA: 0s - loss: 0.1989 - accuracy: 0.9430 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1948 - accuracy: 0.9437 4352/6993 [=================>............] - ETA: 0s - loss: 0.2011 - accuracy: 0.9416 5120/6993 [====================>.........] - ETA: 0s - loss: 0.2016 - accuracy: 0.9416 6016/6993 [========================>.....] - ETA: 0s - loss: 0.2003 - accuracy: 0.9400 6784/6993 [============================>.] - ETA: 0s - loss: 0.2002 - accuracy: 0.9403 6993/6993 [==============================] - 1s 84us/sample - loss: 0.2002 - accuracy: 0.9401 - val_loss: 0.4658 - val_accuracy: 0.8893 Epoch 24/199 128/6993 [..............................] - ETA: 0s - loss: 0.3018 - accuracy: 0.9141 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2033 - accuracy: 0.9404 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1932 - accuracy: 0.9464 2816/6993 [===========>..................] - ETA: 0s - loss: 0.2165 - accuracy: 0.9379 3712/6993 [==============>...............] - ETA: 0s - loss: 0.2087 - accuracy: 0.9405 4480/6993 [==================>...........] - ETA: 0s - loss: 0.2057 - accuracy: 0.9426 5376/6993 [======================>.......] - ETA: 0s - loss: 0.2007 - accuracy: 0.9444 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1955 - accuracy: 0.9461 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1988 - accuracy: 0.9445 - val_loss: 0.4119 - val_accuracy: 0.8969 Epoch 25/199 128/6993 [..............................] - ETA: 0s - loss: 0.1679 - accuracy: 0.9375 896/6993 [==>...........................] - ETA: 0s - loss: 0.1412 - accuracy: 0.9665 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1300 - accuracy: 0.9648 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1499 - accuracy: 0.9594 3456/6993 [=============>................] - ETA: 0s - loss: 0.1658 - accuracy: 0.9543 4352/6993 [=================>............] - ETA: 0s - loss: 0.1705 - accuracy: 0.9508 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1748 - accuracy: 0.9486 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1731 - accuracy: 0.9480 6912/6993 [============================>.] - ETA: 0s - loss: 0.1752 - accuracy: 0.9472 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1738 - accuracy: 0.9477 - val_loss: 0.4172 - val_accuracy: 0.8959 Epoch 26/199 128/6993 [..............................] - ETA: 0s - loss: 0.2454 - accuracy: 0.9297 896/6993 [==>...........................] - ETA: 0s - loss: 0.1443 - accuracy: 0.9576 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1492 - accuracy: 0.9570 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1653 - accuracy: 0.9524 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1654 - accuracy: 0.9520 4352/6993 [=================>............] - ETA: 0s - loss: 0.1787 - accuracy: 0.9481 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1787 - accuracy: 0.9474 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1789 - accuracy: 0.9458 6912/6993 [============================>.] - ETA: 0s - loss: 0.1796 - accuracy: 0.9465 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1786 - accuracy: 0.9467 - val_loss: 0.4072 - val_accuracy: 0.9024 Epoch 27/199 128/6993 [..............................] - ETA: 0s - loss: 0.0618 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1519 - accuracy: 0.9587 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1745 - accuracy: 0.9531 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1762 - accuracy: 0.9512 3456/6993 [=============>................] - ETA: 0s - loss: 0.1758 - accuracy: 0.9517 4224/6993 [=================>............] - ETA: 0s - loss: 0.1855 - accuracy: 0.9505 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1801 - accuracy: 0.9514 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1792 - accuracy: 0.9511 6784/6993 [============================>.] - ETA: 0s - loss: 0.1746 - accuracy: 0.9515 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1734 - accuracy: 0.9521 - val_loss: 0.3923 - val_accuracy: 0.9024 Epoch 28/199 128/6993 [..............................] - ETA: 0s - loss: 0.1509 - accuracy: 0.9531 896/6993 [==>...........................] - ETA: 0s - loss: 0.1235 - accuracy: 0.9654 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1473 - accuracy: 0.9597 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1448 - accuracy: 0.9594 3456/6993 [=============>................] - ETA: 0s - loss: 0.1520 - accuracy: 0.9583 4352/6993 [=================>............] - ETA: 0s - loss: 0.1558 - accuracy: 0.9573 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1609 - accuracy: 0.9561 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1601 - accuracy: 0.9561 6912/6993 [============================>.] - ETA: 0s - loss: 0.1650 - accuracy: 0.9540 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1648 - accuracy: 0.9541 - val_loss: 0.4173 - val_accuracy: 0.9039 Epoch 29/199 128/6993 [..............................] - ETA: 0s - loss: 0.0551 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1275 - accuracy: 0.9668 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1575 - accuracy: 0.9557 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1548 - accuracy: 0.9550 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1624 - accuracy: 0.9537 4352/6993 [=================>............] - ETA: 0s - loss: 0.1678 - accuracy: 0.9529 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1662 - accuracy: 0.9535 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1657 - accuracy: 0.9531 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1669 - accuracy: 0.9531 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1650 - accuracy: 0.9542 6993/6993 [==============================] - 1s 98us/sample - loss: 0.1652 - accuracy: 0.9532 - val_loss: 0.4197 - val_accuracy: 0.8984 Epoch 30/199 128/6993 [..............................] - ETA: 0s - loss: 0.0880 - accuracy: 0.9531 768/6993 [==>...........................] - ETA: 0s - loss: 0.1167 - accuracy: 0.9583 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1095 - accuracy: 0.9652 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1187 - accuracy: 0.9629 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1283 - accuracy: 0.9606 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1333 - accuracy: 0.9591 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1372 - accuracy: 0.9583 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1540 - accuracy: 0.9539 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1534 - accuracy: 0.9546 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1512 - accuracy: 0.9550 - val_loss: 0.4087 - val_accuracy: 0.9065 Epoch 31/199 128/6993 [..............................] - ETA: 0s - loss: 0.1064 - accuracy: 0.9531 896/6993 [==>...........................] - ETA: 0s - loss: 0.1303 - accuracy: 0.9598 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1525 - accuracy: 0.9576 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1658 - accuracy: 0.9542 3456/6993 [=============>................] - ETA: 0s - loss: 0.1619 - accuracy: 0.9549 4096/6993 [================>.............] - ETA: 0s - loss: 0.1569 - accuracy: 0.9551 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1611 - accuracy: 0.9533 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1593 - accuracy: 0.9544 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1539 - accuracy: 0.9557 6993/6993 [==============================] - 1s 82us/sample - loss: 0.1505 - accuracy: 0.9571 - val_loss: 0.3817 - val_accuracy: 0.9151 Epoch 32/199 128/6993 [..............................] - ETA: 0s - loss: 0.0544 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1079 - accuracy: 0.9609 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1282 - accuracy: 0.9554 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1298 - accuracy: 0.9583 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1320 - accuracy: 0.9593 4352/6993 [=================>............] - ETA: 0s - loss: 0.1269 - accuracy: 0.9596 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1290 - accuracy: 0.9594 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1345 - accuracy: 0.9582 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1357 - accuracy: 0.9588 - val_loss: 0.4247 - val_accuracy: 0.9080 Epoch 33/199 128/6993 [..............................] - ETA: 0s - loss: 0.1230 - accuracy: 0.9531 896/6993 [==>...........................] - ETA: 0s - loss: 0.0972 - accuracy: 0.9743 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0956 - accuracy: 0.9754 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1032 - accuracy: 0.9720 3328/6993 [=============>................] - ETA: 0s - loss: 0.1344 - accuracy: 0.9654 4224/6993 [=================>............] - ETA: 0s - loss: 0.1342 - accuracy: 0.9643 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1316 - accuracy: 0.9645 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1331 - accuracy: 0.9645 6784/6993 [============================>.] - ETA: 0s - loss: 0.1301 - accuracy: 0.9651 6993/6993 [==============================] - 1s 77us/sample - loss: 0.1337 - accuracy: 0.9647 - val_loss: 0.4173 - val_accuracy: 0.9024 Epoch 34/199 128/6993 [..............................] - ETA: 0s - loss: 0.1234 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1145 - accuracy: 0.9736 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1147 - accuracy: 0.9694 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1100 - accuracy: 0.9709 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1192 - accuracy: 0.9694 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1185 - accuracy: 0.9688 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1399 - accuracy: 0.9636 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1415 - accuracy: 0.9645 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1384 - accuracy: 0.9638 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1382 - accuracy: 0.9635 - val_loss: 0.4193 - val_accuracy: 0.9075 Epoch 35/199 128/6993 [..............................] - ETA: 0s - loss: 0.1239 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1390 - accuracy: 0.9622 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1316 - accuracy: 0.9570 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1257 - accuracy: 0.9622 3200/6993 [============>.................] - ETA: 0s - loss: 0.1258 - accuracy: 0.9628 3968/6993 [================>.............] - ETA: 0s - loss: 0.1284 - accuracy: 0.9630 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1339 - accuracy: 0.9603 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1331 - accuracy: 0.9609 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1315 - accuracy: 0.9615 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1295 - accuracy: 0.9624 - val_loss: 0.3950 - val_accuracy: 0.9226 Epoch 36/199 128/6993 [..............................] - ETA: 0s - loss: 0.0867 - accuracy: 0.9609 768/6993 [==>...........................] - ETA: 0s - loss: 0.1207 - accuracy: 0.9635 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1117 - accuracy: 0.9674 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1116 - accuracy: 0.9683 3072/6993 [============>.................] - ETA: 0s - loss: 0.1178 - accuracy: 0.9665 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1263 - accuracy: 0.9659 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1261 - accuracy: 0.9671 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1291 - accuracy: 0.9661 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1238 - accuracy: 0.9673 6912/6993 [============================>.] - ETA: 0s - loss: 0.1223 - accuracy: 0.9670 6993/6993 [==============================] - 1s 86us/sample - loss: 0.1217 - accuracy: 0.9673 - val_loss: 0.4178 - val_accuracy: 0.9211 Epoch 37/199 128/6993 [..............................] - ETA: 0s - loss: 0.0570 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1031 - accuracy: 0.9714 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1170 - accuracy: 0.9627 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1299 - accuracy: 0.9655 3200/6993 [============>.................] - ETA: 0s - loss: 0.1246 - accuracy: 0.9669 3968/6993 [================>.............] - ETA: 0s - loss: 0.1267 - accuracy: 0.9660 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1269 - accuracy: 0.9665 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1258 - accuracy: 0.9660 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1235 - accuracy: 0.9665 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1222 - accuracy: 0.9663 - val_loss: 0.4277 - val_accuracy: 0.9151 Epoch 38/199 128/6993 [..............................] - ETA: 0s - loss: 0.0844 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1302 - accuracy: 0.9654 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1316 - accuracy: 0.9665 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1336 - accuracy: 0.9672 3456/6993 [=============>................] - ETA: 0s - loss: 0.1315 - accuracy: 0.9667 4224/6993 [=================>............] - ETA: 0s - loss: 0.1287 - accuracy: 0.9683 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1288 - accuracy: 0.9679 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1292 - accuracy: 0.9667 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1246 - accuracy: 0.9677 6993/6993 [==============================] - 1s 89us/sample - loss: 0.1218 - accuracy: 0.9680 - val_loss: 0.4396 - val_accuracy: 0.9095 Epoch 39/199 128/6993 [..............................] - ETA: 0s - loss: 0.0375 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1705 - accuracy: 0.9727 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1707 - accuracy: 0.9672 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1525 - accuracy: 0.9688 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1362 - accuracy: 0.9695 3200/6993 [============>.................] - ETA: 0s - loss: 0.1346 - accuracy: 0.9700 3968/6993 [================>.............] - ETA: 0s - loss: 0.1337 - accuracy: 0.9693 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1334 - accuracy: 0.9688 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1303 - accuracy: 0.9682 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1253 - accuracy: 0.9694 6993/6993 [==============================] - 1s 92us/sample - loss: 0.1233 - accuracy: 0.9691 - val_loss: 0.4421 - val_accuracy: 0.9110 Epoch 40/199 128/6993 [..............................] - ETA: 0s - loss: 0.2032 - accuracy: 0.9297 896/6993 [==>...........................] - ETA: 0s - loss: 0.1021 - accuracy: 0.9732 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0981 - accuracy: 0.9721 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0915 - accuracy: 0.9746 3456/6993 [=============>................] - ETA: 0s - loss: 0.1134 - accuracy: 0.9690 4352/6993 [=================>............] - ETA: 0s - loss: 0.1157 - accuracy: 0.9662 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1128 - accuracy: 0.9672 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1125 - accuracy: 0.9676 6784/6993 [============================>.] - ETA: 0s - loss: 0.1196 - accuracy: 0.9662 6993/6993 [==============================] - 1s 78us/sample - loss: 0.1213 - accuracy: 0.9663 - val_loss: 0.3919 - val_accuracy: 0.9151 Epoch 41/199 128/6993 [..............................] - ETA: 0s - loss: 0.0563 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0952 - accuracy: 0.9736 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1064 - accuracy: 0.9672 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1088 - accuracy: 0.9677 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1104 - accuracy: 0.9685 4352/6993 [=================>............] - ETA: 0s - loss: 0.1053 - accuracy: 0.9688 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0984 - accuracy: 0.9709 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1078 - accuracy: 0.9701 6784/6993 [============================>.] - ETA: 0s - loss: 0.1048 - accuracy: 0.9702 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1038 - accuracy: 0.9704 - val_loss: 0.4320 - val_accuracy: 0.9186 Epoch 42/199 128/6993 [..............................] - ETA: 0s - loss: 0.1059 - accuracy: 0.9609 768/6993 [==>...........................] - ETA: 0s - loss: 0.1192 - accuracy: 0.9648 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1143 - accuracy: 0.9663 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1161 - accuracy: 0.9650 3200/6993 [============>.................] - ETA: 0s - loss: 0.1171 - accuracy: 0.9659 4096/6993 [================>.............] - ETA: 0s - loss: 0.1188 - accuracy: 0.9673 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1147 - accuracy: 0.9683 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1116 - accuracy: 0.9686 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1156 - accuracy: 0.9671 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1188 - accuracy: 0.9658 - val_loss: 0.4309 - val_accuracy: 0.9075 Epoch 43/199 128/6993 [..............................] - ETA: 0s - loss: 0.0804 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0893 - accuracy: 0.9699 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0952 - accuracy: 0.9710 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0932 - accuracy: 0.9729 3200/6993 [============>.................] - ETA: 0s - loss: 0.0966 - accuracy: 0.9728 4096/6993 [================>.............] - ETA: 0s - loss: 0.1037 - accuracy: 0.9719 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1084 - accuracy: 0.9694 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1055 - accuracy: 0.9696 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1086 - accuracy: 0.9688 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1081 - accuracy: 0.9687 - val_loss: 0.4337 - val_accuracy: 0.9110 Epoch 44/199 128/6993 [..............................] - ETA: 0s - loss: 0.1052 - accuracy: 0.9609 768/6993 [==>...........................] - ETA: 0s - loss: 0.0901 - accuracy: 0.9727 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1030 - accuracy: 0.9724 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1136 - accuracy: 0.9696 3328/6993 [=============>................] - ETA: 0s - loss: 0.1189 - accuracy: 0.9694 4096/6993 [================>.............] - ETA: 0s - loss: 0.1194 - accuracy: 0.9695 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1121 - accuracy: 0.9712 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1151 - accuracy: 0.9711 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1186 - accuracy: 0.9703 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1226 - accuracy: 0.9693 - val_loss: 0.3502 - val_accuracy: 0.9186 Epoch 45/199 128/6993 [..............................] - ETA: 0s - loss: 0.1331 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.0772 - accuracy: 0.9777 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0842 - accuracy: 0.9766 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0890 - accuracy: 0.9773 3456/6993 [=============>................] - ETA: 0s - loss: 0.0914 - accuracy: 0.9754 4352/6993 [=================>............] - ETA: 0s - loss: 0.0998 - accuracy: 0.9745 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0958 - accuracy: 0.9750 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0941 - accuracy: 0.9742 6784/6993 [============================>.] - ETA: 0s - loss: 0.0941 - accuracy: 0.9732 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0953 - accuracy: 0.9724 - val_loss: 0.4461 - val_accuracy: 0.9156 Epoch 46/199 128/6993 [..............................] - ETA: 0s - loss: 0.0613 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0857 - accuracy: 0.9766 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0910 - accuracy: 0.9777 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0943 - accuracy: 0.9754 3456/6993 [=============>................] - ETA: 0s - loss: 0.0897 - accuracy: 0.9751 4224/6993 [=================>............] - ETA: 0s - loss: 0.0916 - accuracy: 0.9749 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0958 - accuracy: 0.9730 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0933 - accuracy: 0.9726 6784/6993 [============================>.] - ETA: 0s - loss: 0.0961 - accuracy: 0.9724 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0972 - accuracy: 0.9723 - val_loss: 0.4288 - val_accuracy: 0.9125 Epoch 47/199 128/6993 [..............................] - ETA: 0s - loss: 0.0644 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1225 - accuracy: 0.9643 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1300 - accuracy: 0.9682 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1412 - accuracy: 0.9691 3456/6993 [=============>................] - ETA: 0s - loss: 0.1268 - accuracy: 0.9722 4224/6993 [=================>............] - ETA: 0s - loss: 0.1335 - accuracy: 0.9704 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1215 - accuracy: 0.9725 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1163 - accuracy: 0.9736 6784/6993 [============================>.] - ETA: 0s - loss: 0.1125 - accuracy: 0.9738 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1110 - accuracy: 0.9743 - val_loss: 0.4348 - val_accuracy: 0.9151 Epoch 48/199 128/6993 [..............................] - ETA: 0s - loss: 0.1932 - accuracy: 0.9531 896/6993 [==>...........................] - ETA: 0s - loss: 0.1375 - accuracy: 0.9743 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1083 - accuracy: 0.9746 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1093 - accuracy: 0.9743 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1028 - accuracy: 0.9751 3328/6993 [=============>................] - ETA: 0s - loss: 0.1015 - accuracy: 0.9754 3968/6993 [================>.............] - ETA: 0s - loss: 0.1021 - accuracy: 0.9756 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1045 - accuracy: 0.9735 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1096 - accuracy: 0.9726 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1093 - accuracy: 0.9725 6784/6993 [============================>.] - ETA: 0s - loss: 0.1083 - accuracy: 0.9723 6993/6993 [==============================] - 1s 96us/sample - loss: 0.1084 - accuracy: 0.9718 - val_loss: 0.4751 - val_accuracy: 0.9130 Epoch 49/199 128/6993 [..............................] - ETA: 0s - loss: 0.0818 - accuracy: 0.9609 512/6993 [=>............................] - ETA: 0s - loss: 0.0864 - accuracy: 0.9727 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1032 - accuracy: 0.9750 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0951 - accuracy: 0.9761 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1010 - accuracy: 0.9745 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1016 - accuracy: 0.9736 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1034 - accuracy: 0.9723 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0968 - accuracy: 0.9730 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0987 - accuracy: 0.9726 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0982 - accuracy: 0.9728 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0988 - accuracy: 0.9728 - val_loss: 0.4309 - val_accuracy: 0.9105 Epoch 50/199 128/6993 [..............................] - ETA: 0s - loss: 0.0907 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0571 - accuracy: 0.9805 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0703 - accuracy: 0.9766 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0891 - accuracy: 0.9771 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0984 - accuracy: 0.9758 3328/6993 [=============>................] - ETA: 0s - loss: 0.0888 - accuracy: 0.9775 3968/6993 [================>.............] - ETA: 0s - loss: 0.0872 - accuracy: 0.9766 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0833 - accuracy: 0.9770 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0869 - accuracy: 0.9758 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0907 - accuracy: 0.9756 6912/6993 [============================>.] - ETA: 0s - loss: 0.0940 - accuracy: 0.9742 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0931 - accuracy: 0.9745 - val_loss: 0.4351 - val_accuracy: 0.9141 Epoch 51/199 128/6993 [..............................] - ETA: 0s - loss: 0.1077 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0997 - accuracy: 0.9766 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0961 - accuracy: 0.9821 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0920 - accuracy: 0.9805 3456/6993 [=============>................] - ETA: 0s - loss: 0.0824 - accuracy: 0.9823 4224/6993 [=================>............] - ETA: 0s - loss: 0.0801 - accuracy: 0.9825 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0916 - accuracy: 0.9791 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0907 - accuracy: 0.9792 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0949 - accuracy: 0.9779 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0946 - accuracy: 0.9777 - val_loss: 0.4313 - val_accuracy: 0.9196 Epoch 52/199 128/6993 [..............................] - ETA: 0s - loss: 0.0643 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0616 - accuracy: 0.9766 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0724 - accuracy: 0.9766 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0828 - accuracy: 0.9762 3456/6993 [=============>................] - ETA: 0s - loss: 0.0877 - accuracy: 0.9757 4352/6993 [=================>............] - ETA: 0s - loss: 0.0864 - accuracy: 0.9759 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0905 - accuracy: 0.9752 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0945 - accuracy: 0.9752 6912/6993 [============================>.] - ETA: 0s - loss: 0.0907 - accuracy: 0.9763 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0906 - accuracy: 0.9760 - val_loss: 0.4651 - val_accuracy: 0.9130 Epoch 53/199 128/6993 [..............................] - ETA: 0s - loss: 0.0536 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0970 - accuracy: 0.9746 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0915 - accuracy: 0.9760 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0888 - accuracy: 0.9769 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1048 - accuracy: 0.9749 4352/6993 [=================>............] - ETA: 0s - loss: 0.1031 - accuracy: 0.9733 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0982 - accuracy: 0.9738 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0985 - accuracy: 0.9745 6784/6993 [============================>.] - ETA: 0s - loss: 0.1063 - accuracy: 0.9733 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1052 - accuracy: 0.9734 - val_loss: 0.4328 - val_accuracy: 0.9141 Epoch 54/199 128/6993 [..............................] - ETA: 0s - loss: 0.0466 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0898 - accuracy: 0.9721 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0767 - accuracy: 0.9777 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0725 - accuracy: 0.9789 3456/6993 [=============>................] - ETA: 0s - loss: 0.0711 - accuracy: 0.9783 4352/6993 [=================>............] - ETA: 0s - loss: 0.0770 - accuracy: 0.9777 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0758 - accuracy: 0.9770 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0838 - accuracy: 0.9753 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0894 - accuracy: 0.9746 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0910 - accuracy: 0.9748 - val_loss: 0.4820 - val_accuracy: 0.9085 Epoch 55/199 128/6993 [..............................] - ETA: 0s - loss: 0.1495 - accuracy: 0.9531 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0930 - accuracy: 0.9727 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0977 - accuracy: 0.9724 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0848 - accuracy: 0.9742 3456/6993 [=============>................] - ETA: 0s - loss: 0.0793 - accuracy: 0.9757 4224/6993 [=================>............] - ETA: 0s - loss: 0.0843 - accuracy: 0.9754 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0948 - accuracy: 0.9744 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0952 - accuracy: 0.9752 6784/6993 [============================>.] - ETA: 0s - loss: 0.0863 - accuracy: 0.9772 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0848 - accuracy: 0.9774 - val_loss: 0.4502 - val_accuracy: 0.9232 Epoch 56/199 128/6993 [..............................] - ETA: 0s - loss: 0.0089 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0815 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0905 - accuracy: 0.9799 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0815 - accuracy: 0.9814 3456/6993 [=============>................] - ETA: 0s - loss: 0.0851 - accuracy: 0.9795 4224/6993 [=================>............] - ETA: 0s - loss: 0.0787 - accuracy: 0.9804 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0856 - accuracy: 0.9784 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0851 - accuracy: 0.9774 6784/6993 [============================>.] - ETA: 0s - loss: 0.0888 - accuracy: 0.9772 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0878 - accuracy: 0.9774 - val_loss: 0.4477 - val_accuracy: 0.9090 Epoch 57/199 128/6993 [..............................] - ETA: 0s - loss: 0.0170 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1035 - accuracy: 0.9754 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0892 - accuracy: 0.9760 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0784 - accuracy: 0.9773 3328/6993 [=============>................] - ETA: 0s - loss: 0.0740 - accuracy: 0.9796 4096/6993 [================>.............] - ETA: 0s - loss: 0.0760 - accuracy: 0.9788 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0743 - accuracy: 0.9789 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0744 - accuracy: 0.9797 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0736 - accuracy: 0.9797 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0787 - accuracy: 0.9789 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0780 - accuracy: 0.9788 - val_loss: 0.5107 - val_accuracy: 0.9095 Epoch 58/199 128/6993 [..............................] - ETA: 0s - loss: 0.0290 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0640 - accuracy: 0.9877 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0595 - accuracy: 0.9883 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0653 - accuracy: 0.9840 3328/6993 [=============>................] - ETA: 0s - loss: 0.0648 - accuracy: 0.9835 4224/6993 [=================>............] - ETA: 0s - loss: 0.0731 - accuracy: 0.9808 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0713 - accuracy: 0.9805 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0870 - accuracy: 0.9766 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0880 - accuracy: 0.9754 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0860 - accuracy: 0.9760 - val_loss: 0.4337 - val_accuracy: 0.9181 Epoch 59/199 128/6993 [..............................] - ETA: 0s - loss: 0.0149 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0646 - accuracy: 0.9754 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0678 - accuracy: 0.9759 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0696 - accuracy: 0.9774 3200/6993 [============>.................] - ETA: 0s - loss: 0.0750 - accuracy: 0.9781 3968/6993 [================>.............] - ETA: 0s - loss: 0.0724 - accuracy: 0.9798 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0752 - accuracy: 0.9791 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0769 - accuracy: 0.9787 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0757 - accuracy: 0.9786 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0831 - accuracy: 0.9783 - val_loss: 0.4991 - val_accuracy: 0.9090 Epoch 60/199 128/6993 [..............................] - ETA: 0s - loss: 0.0385 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0717 - accuracy: 0.9799 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0683 - accuracy: 0.9802 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0680 - accuracy: 0.9820 3456/6993 [=============>................] - ETA: 0s - loss: 0.0723 - accuracy: 0.9809 4352/6993 [=================>............] - ETA: 0s - loss: 0.0736 - accuracy: 0.9800 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0773 - accuracy: 0.9783 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0778 - accuracy: 0.9782 6912/6993 [============================>.] - ETA: 0s - loss: 0.0818 - accuracy: 0.9770 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0817 - accuracy: 0.9770 - val_loss: 0.4244 - val_accuracy: 0.9151 Epoch 61/199 128/6993 [..............................] - ETA: 0s - loss: 0.0999 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0918 - accuracy: 0.9781 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0907 - accuracy: 0.9766 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1028 - accuracy: 0.9748 3072/6993 [============>.................] - ETA: 0s - loss: 0.0961 - accuracy: 0.9759 3968/6993 [================>.............] - ETA: 0s - loss: 0.0815 - accuracy: 0.9791 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0766 - accuracy: 0.9799 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0818 - accuracy: 0.9790 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0821 - accuracy: 0.9786 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0817 - accuracy: 0.9790 - val_loss: 0.4332 - val_accuracy: 0.9191 Epoch 62/199 128/6993 [..............................] - ETA: 0s - loss: 0.0885 - accuracy: 0.9688 1152/6993 [===>..........................] - ETA: 0s - loss: 0.1002 - accuracy: 0.9757 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0893 - accuracy: 0.9776 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0923 - accuracy: 0.9751 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0801 - accuracy: 0.9782 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0799 - accuracy: 0.9783 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0816 - accuracy: 0.9781 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0844 - accuracy: 0.9770 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0825 - accuracy: 0.9777 - val_loss: 0.4469 - val_accuracy: 0.9196 Epoch 63/199 128/6993 [..............................] - ETA: 0s - loss: 0.0503 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0815 - accuracy: 0.9824 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0774 - accuracy: 0.9786 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0768 - accuracy: 0.9784 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0703 - accuracy: 0.9816 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0749 - accuracy: 0.9801 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0778 - accuracy: 0.9794 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0765 - accuracy: 0.9801 6784/6993 [============================>.] - ETA: 0s - loss: 0.0783 - accuracy: 0.9797 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0785 - accuracy: 0.9796 - val_loss: 0.4547 - val_accuracy: 0.9186 Epoch 64/199 128/6993 [..............................] - ETA: 0s - loss: 0.1277 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0905 - accuracy: 0.9805 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0716 - accuracy: 0.9811 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0612 - accuracy: 0.9811 3200/6993 [============>.................] - ETA: 0s - loss: 0.0644 - accuracy: 0.9819 4096/6993 [================>.............] - ETA: 0s - loss: 0.0688 - accuracy: 0.9800 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0884 - accuracy: 0.9788 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0884 - accuracy: 0.9783 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0870 - accuracy: 0.9783 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0881 - accuracy: 0.9784 - val_loss: 0.5030 - val_accuracy: 0.9130 Epoch 65/199 128/6993 [..............................] - ETA: 0s - loss: 0.0403 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0698 - accuracy: 0.9805 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0617 - accuracy: 0.9818 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0730 - accuracy: 0.9825 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0691 - accuracy: 0.9835 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0810 - accuracy: 0.9812 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0776 - accuracy: 0.9821 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0760 - accuracy: 0.9819 6912/6993 [============================>.] - ETA: 0s - loss: 0.0799 - accuracy: 0.9810 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0793 - accuracy: 0.9811 - val_loss: 0.5333 - val_accuracy: 0.9100 Epoch 66/199 128/6993 [..............................] - ETA: 0s - loss: 0.0860 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0850 - accuracy: 0.9821 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0995 - accuracy: 0.9816 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0931 - accuracy: 0.9797 3456/6993 [=============>................] - ETA: 0s - loss: 0.0864 - accuracy: 0.9792 4352/6993 [=================>............] - ETA: 0s - loss: 0.0982 - accuracy: 0.9789 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0912 - accuracy: 0.9803 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0888 - accuracy: 0.9809 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0888 - accuracy: 0.9806 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0886 - accuracy: 0.9807 - val_loss: 0.4501 - val_accuracy: 0.9186 Epoch 67/199 128/6993 [..............................] - ETA: 0s - loss: 0.1239 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0380 - accuracy: 0.9922 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0423 - accuracy: 0.9867 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0542 - accuracy: 0.9854 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0606 - accuracy: 0.9840 3200/6993 [============>.................] - ETA: 0s - loss: 0.0713 - accuracy: 0.9831 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0653 - accuracy: 0.9841 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0670 - accuracy: 0.9833 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0685 - accuracy: 0.9825 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0688 - accuracy: 0.9824 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0715 - accuracy: 0.9816 - val_loss: 0.4221 - val_accuracy: 0.9181 Epoch 68/199 128/6993 [..............................] - ETA: 0s - loss: 0.0522 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0772 - accuracy: 0.9777 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0898 - accuracy: 0.9788 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0822 - accuracy: 0.9795 3328/6993 [=============>................] - ETA: 0s - loss: 0.0817 - accuracy: 0.9790 4096/6993 [================>.............] - ETA: 0s - loss: 0.0809 - accuracy: 0.9785 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0774 - accuracy: 0.9796 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0808 - accuracy: 0.9793 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0797 - accuracy: 0.9802 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0803 - accuracy: 0.9803 - val_loss: 0.4490 - val_accuracy: 0.9156 Epoch 69/199 128/6993 [..............................] - ETA: 0s - loss: 0.0192 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0616 - accuracy: 0.9814 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0684 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0655 - accuracy: 0.9833 3328/6993 [=============>................] - ETA: 0s - loss: 0.0661 - accuracy: 0.9841 4224/6993 [=================>............] - ETA: 0s - loss: 0.0703 - accuracy: 0.9827 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0799 - accuracy: 0.9803 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0771 - accuracy: 0.9800 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0875 - accuracy: 0.9793 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0848 - accuracy: 0.9797 - val_loss: 0.4709 - val_accuracy: 0.9211 Epoch 70/199 128/6993 [..............................] - ETA: 0s - loss: 0.0760 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0577 - accuracy: 0.9854 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0641 - accuracy: 0.9839 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0762 - accuracy: 0.9809 3456/6993 [=============>................] - ETA: 0s - loss: 0.0824 - accuracy: 0.9800 4224/6993 [=================>............] - ETA: 0s - loss: 0.0786 - accuracy: 0.9806 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0810 - accuracy: 0.9797 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0801 - accuracy: 0.9807 6912/6993 [============================>.] - ETA: 0s - loss: 0.0783 - accuracy: 0.9813 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0787 - accuracy: 0.9810 - val_loss: 0.5258 - val_accuracy: 0.9186 Epoch 71/199 128/6993 [..............................] - ETA: 0s - loss: 0.0438 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0663 - accuracy: 0.9833 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0710 - accuracy: 0.9810 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0638 - accuracy: 0.9819 3328/6993 [=============>................] - ETA: 0s - loss: 0.0631 - accuracy: 0.9811 4096/6993 [================>.............] - ETA: 0s - loss: 0.0641 - accuracy: 0.9810 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0677 - accuracy: 0.9810 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0661 - accuracy: 0.9818 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0656 - accuracy: 0.9818 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0678 - accuracy: 0.9817 - val_loss: 0.4856 - val_accuracy: 0.9171 Epoch 72/199 128/6993 [..............................] - ETA: 0s - loss: 0.0657 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0661 - accuracy: 0.9844 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0643 - accuracy: 0.9823 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0657 - accuracy: 0.9847 3456/6993 [=============>................] - ETA: 0s - loss: 0.0600 - accuracy: 0.9864 4352/6993 [=================>............] - ETA: 0s - loss: 0.0700 - accuracy: 0.9835 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0796 - accuracy: 0.9821 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0831 - accuracy: 0.9809 6912/6993 [============================>.] - ETA: 0s - loss: 0.0809 - accuracy: 0.9810 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0800 - accuracy: 0.9813 - val_loss: 0.4678 - val_accuracy: 0.9181 Epoch 73/199 128/6993 [..............................] - ETA: 0s - loss: 0.0783 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1131 - accuracy: 0.9810 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0896 - accuracy: 0.9798 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0746 - accuracy: 0.9840 3200/6993 [============>.................] - ETA: 0s - loss: 0.0683 - accuracy: 0.9844 4096/6993 [================>.............] - ETA: 0s - loss: 0.0730 - accuracy: 0.9829 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0819 - accuracy: 0.9818 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0802 - accuracy: 0.9825 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0771 - accuracy: 0.9830 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0784 - accuracy: 0.9830 - val_loss: 0.4751 - val_accuracy: 0.9135 Epoch 74/199 128/6993 [..............................] - ETA: 0s - loss: 0.0298 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0832 - accuracy: 0.9834 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0870 - accuracy: 0.9799 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0912 - accuracy: 0.9793 3456/6993 [=============>................] - ETA: 0s - loss: 0.0806 - accuracy: 0.9815 4224/6993 [=================>............] - ETA: 0s - loss: 0.0840 - accuracy: 0.9804 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0757 - accuracy: 0.9820 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0830 - accuracy: 0.9815 6784/6993 [============================>.] - ETA: 0s - loss: 0.0842 - accuracy: 0.9816 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0835 - accuracy: 0.9814 - val_loss: 0.5051 - val_accuracy: 0.9181 Epoch 75/199 128/6993 [..............................] - ETA: 0s - loss: 0.0587 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0945 - accuracy: 0.9766 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0832 - accuracy: 0.9777 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0673 - accuracy: 0.9810 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0771 - accuracy: 0.9810 4352/6993 [=================>............] - ETA: 0s - loss: 0.0774 - accuracy: 0.9818 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0787 - accuracy: 0.9821 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0754 - accuracy: 0.9821 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0699 - accuracy: 0.9831 - val_loss: 0.5180 - val_accuracy: 0.9161 Epoch 76/199 128/6993 [..............................] - ETA: 0s - loss: 0.0060 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0913 - accuracy: 0.9805 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0856 - accuracy: 0.9805 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0776 - accuracy: 0.9836 3072/6993 [============>.................] - ETA: 0s - loss: 0.0763 - accuracy: 0.9840 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0782 - accuracy: 0.9833 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0788 - accuracy: 0.9824 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0768 - accuracy: 0.9824 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0742 - accuracy: 0.9826 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0746 - accuracy: 0.9827 6912/6993 [============================>.] - ETA: 0s - loss: 0.0739 - accuracy: 0.9828 6993/6993 [==============================] - 1s 97us/sample - loss: 0.0738 - accuracy: 0.9826 - val_loss: 0.4771 - val_accuracy: 0.9196 Epoch 77/199 128/6993 [..............................] - ETA: 0s - loss: 0.0230 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0771 - accuracy: 0.9779 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9818 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0757 - accuracy: 0.9803 3328/6993 [=============>................] - ETA: 0s - loss: 0.0841 - accuracy: 0.9796 4224/6993 [=================>............] - ETA: 0s - loss: 0.0852 - accuracy: 0.9794 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0878 - accuracy: 0.9795 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0862 - accuracy: 0.9795 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0827 - accuracy: 0.9800 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0797 - accuracy: 0.9808 - val_loss: 0.4052 - val_accuracy: 0.9277 Epoch 78/199 128/6993 [..............................] - ETA: 0s - loss: 0.0267 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0570 - accuracy: 0.9863 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0672 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0921 - accuracy: 0.9807 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0926 - accuracy: 0.9794 4352/6993 [=================>............] - ETA: 0s - loss: 0.0919 - accuracy: 0.9789 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0863 - accuracy: 0.9804 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0848 - accuracy: 0.9806 6784/6993 [============================>.] - ETA: 0s - loss: 0.0836 - accuracy: 0.9811 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0822 - accuracy: 0.9816 - val_loss: 0.4767 - val_accuracy: 0.9226 Epoch 79/199 128/6993 [..............................] - ETA: 0s - loss: 0.0081 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0887 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0778 - accuracy: 0.9866 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0799 - accuracy: 0.9840 3456/6993 [=============>................] - ETA: 0s - loss: 0.0757 - accuracy: 0.9835 4352/6993 [=================>............] - ETA: 0s - loss: 0.0774 - accuracy: 0.9823 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0749 - accuracy: 0.9820 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0852 - accuracy: 0.9812 6784/6993 [============================>.] - ETA: 0s - loss: 0.0844 - accuracy: 0.9817 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0839 - accuracy: 0.9816 - val_loss: 0.4358 - val_accuracy: 0.9282 Epoch 80/199 128/6993 [..............................] - ETA: 0s - loss: 0.0880 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0663 - accuracy: 0.9824 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0605 - accuracy: 0.9839 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0506 - accuracy: 0.9866 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0568 - accuracy: 0.9858 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0619 - accuracy: 0.9848 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0680 - accuracy: 0.9836 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0682 - accuracy: 0.9834 6784/6993 [============================>.] - ETA: 0s - loss: 0.0653 - accuracy: 0.9842 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0710 - accuracy: 0.9840 - val_loss: 0.5157 - val_accuracy: 0.9176 Epoch 81/199 128/6993 [..............................] - ETA: 0s - loss: 0.0226 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1031 - accuracy: 0.9777 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0949 - accuracy: 0.9816 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0792 - accuracy: 0.9829 3456/6993 [=============>................] - ETA: 0s - loss: 0.0748 - accuracy: 0.9844 4224/6993 [=================>............] - ETA: 0s - loss: 0.0652 - accuracy: 0.9858 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0658 - accuracy: 0.9858 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0666 - accuracy: 0.9853 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0683 - accuracy: 0.9855 6912/6993 [============================>.] - ETA: 0s - loss: 0.0661 - accuracy: 0.9854 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0670 - accuracy: 0.9854 - val_loss: 0.5680 - val_accuracy: 0.9151 Epoch 82/199 128/6993 [..............................] - ETA: 0s - loss: 0.0497 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0979 - accuracy: 0.9810 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0843 - accuracy: 0.9844 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0698 - accuracy: 0.9856 3328/6993 [=============>................] - ETA: 0s - loss: 0.0665 - accuracy: 0.9838 3968/6993 [================>.............] - ETA: 0s - loss: 0.0780 - accuracy: 0.9826 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0739 - accuracy: 0.9835 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0730 - accuracy: 0.9833 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0718 - accuracy: 0.9832 6784/6993 [============================>.] - ETA: 0s - loss: 0.0717 - accuracy: 0.9825 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0736 - accuracy: 0.9821 - val_loss: 0.5008 - val_accuracy: 0.9166 Epoch 83/199 128/6993 [..............................] - ETA: 0s - loss: 0.0120 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0416 - accuracy: 0.9877 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0655 - accuracy: 0.9856 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0681 - accuracy: 0.9855 3456/6993 [=============>................] - ETA: 0s - loss: 0.0704 - accuracy: 0.9844 4224/6993 [=================>............] - ETA: 0s - loss: 0.0746 - accuracy: 0.9830 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0728 - accuracy: 0.9834 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0728 - accuracy: 0.9830 6784/6993 [============================>.] - ETA: 0s - loss: 0.0701 - accuracy: 0.9836 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0694 - accuracy: 0.9838 - val_loss: 0.5149 - val_accuracy: 0.9161 Epoch 84/199 128/6993 [..............................] - ETA: 0s - loss: 0.0518 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0527 - accuracy: 0.9863 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0609 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0805 - accuracy: 0.9847 3456/6993 [=============>................] - ETA: 0s - loss: 0.0680 - accuracy: 0.9867 4224/6993 [=================>............] - ETA: 0s - loss: 0.0702 - accuracy: 0.9853 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0777 - accuracy: 0.9830 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0799 - accuracy: 0.9830 6784/6993 [============================>.] - ETA: 0s - loss: 0.0739 - accuracy: 0.9836 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0738 - accuracy: 0.9840 - val_loss: 0.5055 - val_accuracy: 0.9196 Epoch 85/199 128/6993 [..............................] - ETA: 0s - loss: 0.0075 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0471 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0576 - accuracy: 0.9860 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0523 - accuracy: 0.9885 3456/6993 [=============>................] - ETA: 0s - loss: 0.0537 - accuracy: 0.9887 4352/6993 [=================>............] - ETA: 0s - loss: 0.0531 - accuracy: 0.9876 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0668 - accuracy: 0.9852 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0650 - accuracy: 0.9854 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0662 - accuracy: 0.9847 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0671 - accuracy: 0.9846 - val_loss: 0.5344 - val_accuracy: 0.9146 Epoch 86/199 128/6993 [..............................] - ETA: 0s - loss: 0.0724 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.1224 - accuracy: 0.9797 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1364 - accuracy: 0.9789 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1256 - accuracy: 0.9797 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1240 - accuracy: 0.9801 3328/6993 [=============>................] - ETA: 0s - loss: 0.1128 - accuracy: 0.9790 4096/6993 [================>.............] - ETA: 0s - loss: 0.1040 - accuracy: 0.9790 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0925 - accuracy: 0.9810 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0962 - accuracy: 0.9809 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1083 - accuracy: 0.9803 6993/6993 [==============================] - 1s 89us/sample - loss: 0.1069 - accuracy: 0.9803 - val_loss: 0.5038 - val_accuracy: 0.9151 Epoch 87/199 128/6993 [..............................] - ETA: 0s - loss: 0.0119 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0515 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0500 - accuracy: 0.9874 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0577 - accuracy: 0.9855 3456/6993 [=============>................] - ETA: 0s - loss: 0.0596 - accuracy: 0.9852 4352/6993 [=================>............] - ETA: 0s - loss: 0.0635 - accuracy: 0.9841 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0670 - accuracy: 0.9821 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0713 - accuracy: 0.9811 6912/6993 [============================>.] - ETA: 0s - loss: 0.0655 - accuracy: 0.9822 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0664 - accuracy: 0.9823 - val_loss: 0.4774 - val_accuracy: 0.9221 Epoch 88/199 128/6993 [..............................] - ETA: 0s - loss: 0.0376 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0632 - accuracy: 0.9844 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0708 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0752 - accuracy: 0.9825 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0650 - accuracy: 0.9838 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0698 - accuracy: 0.9821 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0658 - accuracy: 0.9829 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0644 - accuracy: 0.9834 6912/6993 [============================>.] - ETA: 0s - loss: 0.0645 - accuracy: 0.9835 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0644 - accuracy: 0.9834 - val_loss: 0.4859 - val_accuracy: 0.9221 Epoch 89/199 128/6993 [..............................] - ETA: 0s - loss: 0.0154 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0777 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0584 - accuracy: 0.9866 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0595 - accuracy: 0.9871 3328/6993 [=============>................] - ETA: 0s - loss: 0.0613 - accuracy: 0.9868 4224/6993 [=================>............] - ETA: 0s - loss: 0.0698 - accuracy: 0.9851 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0655 - accuracy: 0.9854 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0663 - accuracy: 0.9852 6784/6993 [============================>.] - ETA: 0s - loss: 0.0640 - accuracy: 0.9854 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0644 - accuracy: 0.9853 - val_loss: 0.5722 - val_accuracy: 0.9161 Epoch 90/199 128/6993 [..............................] - ETA: 0s - loss: 0.1098 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0423 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0684 - accuracy: 0.9855 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0868 - accuracy: 0.9844 3328/6993 [=============>................] - ETA: 0s - loss: 0.0869 - accuracy: 0.9841 4224/6993 [=================>............] - ETA: 0s - loss: 0.0787 - accuracy: 0.9844 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0851 - accuracy: 0.9826 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0860 - accuracy: 0.9810 6784/6993 [============================>.] - ETA: 0s - loss: 0.0848 - accuracy: 0.9816 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0840 - accuracy: 0.9816 - val_loss: 0.4728 - val_accuracy: 0.9287 Epoch 91/199 128/6993 [..............................] - ETA: 0s - loss: 0.0241 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0383 - accuracy: 0.9855 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0371 - accuracy: 0.9880 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0445 - accuracy: 0.9879 3328/6993 [=============>................] - ETA: 0s - loss: 0.0436 - accuracy: 0.9880 4224/6993 [=================>............] - ETA: 0s - loss: 0.0473 - accuracy: 0.9877 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0485 - accuracy: 0.9880 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0556 - accuracy: 0.9871 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0596 - accuracy: 0.9868 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0571 - accuracy: 0.9873 - val_loss: 0.5457 - val_accuracy: 0.9181 Epoch 92/199 128/6993 [..............................] - ETA: 0s - loss: 0.0027 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0443 - accuracy: 0.9873 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0676 - accuracy: 0.9838 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0712 - accuracy: 0.9844 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0648 - accuracy: 0.9852 4352/6993 [=================>............] - ETA: 0s - loss: 0.0645 - accuracy: 0.9846 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0720 - accuracy: 0.9846 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0754 - accuracy: 0.9839 6912/6993 [============================>.] - ETA: 0s - loss: 0.0745 - accuracy: 0.9842 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0740 - accuracy: 0.9843 - val_loss: 0.5769 - val_accuracy: 0.9151 Epoch 93/199 128/6993 [..............................] - ETA: 0s - loss: 0.0802 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0486 - accuracy: 0.9877 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0855 - accuracy: 0.9855 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0752 - accuracy: 0.9863 3456/6993 [=============>................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9855 4224/6993 [=================>............] - ETA: 0s - loss: 0.0760 - accuracy: 0.9837 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0751 - accuracy: 0.9838 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0791 - accuracy: 0.9837 6784/6993 [============================>.] - ETA: 0s - loss: 0.0805 - accuracy: 0.9823 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0802 - accuracy: 0.9821 - val_loss: 0.5132 - val_accuracy: 0.9307 Epoch 94/199 128/6993 [..............................] - ETA: 0s - loss: 0.0414 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0462 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0489 - accuracy: 0.9856 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0520 - accuracy: 0.9883 3328/6993 [=============>................] - ETA: 0s - loss: 0.0646 - accuracy: 0.9871 4096/6993 [================>.............] - ETA: 0s - loss: 0.0646 - accuracy: 0.9871 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0616 - accuracy: 0.9870 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0609 - accuracy: 0.9856 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0670 - accuracy: 0.9850 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0681 - accuracy: 0.9843 - val_loss: 0.5596 - val_accuracy: 0.9237 Epoch 95/199 128/6993 [..............................] - ETA: 0s - loss: 0.0703 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1689 - accuracy: 0.9844 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1074 - accuracy: 0.9837 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0834 - accuracy: 0.9857 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0760 - accuracy: 0.9869 3456/6993 [=============>................] - ETA: 0s - loss: 0.0801 - accuracy: 0.9867 4096/6993 [================>.............] - ETA: 0s - loss: 0.0741 - accuracy: 0.9873 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0712 - accuracy: 0.9863 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0661 - accuracy: 0.9867 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0734 - accuracy: 0.9857 6784/6993 [============================>.] - ETA: 0s - loss: 0.0709 - accuracy: 0.9857 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0713 - accuracy: 0.9857 - val_loss: 0.5885 - val_accuracy: 0.9171 Epoch 96/199 128/6993 [..............................] - ETA: 0s - loss: 0.1661 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0729 - accuracy: 0.9824 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0673 - accuracy: 0.9839 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0741 - accuracy: 0.9822 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0744 - accuracy: 0.9830 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0750 - accuracy: 0.9837 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0713 - accuracy: 0.9844 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0770 - accuracy: 0.9842 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0774 - accuracy: 0.9838 - val_loss: 0.4925 - val_accuracy: 0.9272 Epoch 97/199 128/6993 [..............................] - ETA: 0s - loss: 0.0188 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0591 - accuracy: 0.9844 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0615 - accuracy: 0.9854 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0492 - accuracy: 0.9879 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0488 - accuracy: 0.9880 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0485 - accuracy: 0.9866 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0545 - accuracy: 0.9855 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0614 - accuracy: 0.9844 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0601 - accuracy: 0.9840 - val_loss: 0.5061 - val_accuracy: 0.9267 Epoch 98/199 128/6993 [..............................] - ETA: 0s - loss: 0.1354 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0995 - accuracy: 0.9821 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1015 - accuracy: 0.9832 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0890 - accuracy: 0.9828 3328/6993 [=============>................] - ETA: 0s - loss: 0.0708 - accuracy: 0.9868 4224/6993 [=================>............] - ETA: 0s - loss: 0.0616 - accuracy: 0.9879 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0717 - accuracy: 0.9877 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0680 - accuracy: 0.9878 6784/6993 [============================>.] - ETA: 0s - loss: 0.0679 - accuracy: 0.9884 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0667 - accuracy: 0.9884 - val_loss: 0.6154 - val_accuracy: 0.9196 Epoch 99/199 128/6993 [..............................] - ETA: 0s - loss: 0.0660 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0778 - accuracy: 0.9863 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0907 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0788 - accuracy: 0.9851 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0717 - accuracy: 0.9860 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0692 - accuracy: 0.9864 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0673 - accuracy: 0.9861 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0669 - accuracy: 0.9865 6912/6993 [============================>.] - ETA: 0s - loss: 0.0692 - accuracy: 0.9865 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0692 - accuracy: 0.9864 - val_loss: 0.5976 - val_accuracy: 0.9257 Epoch 100/199 128/6993 [..............................] - ETA: 0s - loss: 6.7883e-04 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0272 - accuracy: 0.9932 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0623 - accuracy: 0.9906 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0773 - accuracy: 0.9896 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0724 - accuracy: 0.9883 4352/6993 [=================>............] - ETA: 0s - loss: 0.0749 - accuracy: 0.9885 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0822 - accuracy: 0.9876 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0848 - accuracy: 0.9869 6912/6993 [============================>.] - ETA: 0s - loss: 0.0841 - accuracy: 0.9868 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0831 - accuracy: 0.9870 - val_loss: 0.5771 - val_accuracy: 0.9221 Epoch 101/199 128/6993 [..............................] - ETA: 0s - loss: 0.0014 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0639 - accuracy: 0.9873 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0508 - accuracy: 0.9877 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0514 - accuracy: 0.9887 3200/6993 [============>.................] - ETA: 0s - loss: 0.0624 - accuracy: 0.9866 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0611 - accuracy: 0.9862 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0646 - accuracy: 0.9859 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0675 - accuracy: 0.9853 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0701 - accuracy: 0.9844 6784/6993 [============================>.] - ETA: 0s - loss: 0.0697 - accuracy: 0.9841 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0679 - accuracy: 0.9844 - val_loss: 0.5548 - val_accuracy: 0.9237 Epoch 102/199 128/6993 [..............................] - ETA: 0s - loss: 0.0417 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0790 - accuracy: 0.9821 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0729 - accuracy: 0.9828 3456/6993 [=============>................] - ETA: 0s - loss: 0.0751 - accuracy: 0.9844 4224/6993 [=================>............] - ETA: 0s - loss: 0.0679 - accuracy: 0.9853 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0608 - accuracy: 0.9863 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0624 - accuracy: 0.9866 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0576 - accuracy: 0.9877 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0562 - accuracy: 0.9878 - val_loss: 0.5827 - val_accuracy: 0.9272 Epoch 103/199 128/6993 [..............................] - ETA: 0s - loss: 0.0746 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0888 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0720 - accuracy: 0.9877 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0910 - accuracy: 0.9877 3456/6993 [=============>................] - ETA: 0s - loss: 0.0920 - accuracy: 0.9850 4352/6993 [=================>............] - ETA: 0s - loss: 0.0822 - accuracy: 0.9848 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0812 - accuracy: 0.9848 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0846 - accuracy: 0.9850 6912/6993 [============================>.] - ETA: 0s - loss: 0.0820 - accuracy: 0.9852 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0816 - accuracy: 0.9853 - val_loss: 0.5663 - val_accuracy: 0.9257 Epoch 104/199 128/6993 [..............................] - ETA: 0s - loss: 0.0650 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0617 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0744 - accuracy: 0.9860 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0726 - accuracy: 0.9859 3328/6993 [=============>................] - ETA: 0s - loss: 0.0724 - accuracy: 0.9853 4096/6993 [================>.............] - ETA: 0s - loss: 0.0671 - accuracy: 0.9856 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0679 - accuracy: 0.9858 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0693 - accuracy: 0.9857 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0780 - accuracy: 0.9850 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0767 - accuracy: 0.9854 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0774 - accuracy: 0.9853 - val_loss: 0.6136 - val_accuracy: 0.9105 Epoch 105/199 128/6993 [..............................] - ETA: 0s - loss: 0.0614 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.0932 - accuracy: 0.9766 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0778 - accuracy: 0.9822 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0689 - accuracy: 0.9839 3072/6993 [============>.................] - ETA: 0s - loss: 0.0664 - accuracy: 0.9857 3968/6993 [================>.............] - ETA: 0s - loss: 0.0622 - accuracy: 0.9864 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0576 - accuracy: 0.9868 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0598 - accuracy: 0.9865 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0576 - accuracy: 0.9862 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0580 - accuracy: 0.9863 - val_loss: 0.6239 - val_accuracy: 0.9302 Epoch 106/199 128/6993 [..............................] - ETA: 0s - loss: 0.0677 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0341 - accuracy: 0.9855 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0330 - accuracy: 0.9862 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0502 - accuracy: 0.9855 3456/6993 [=============>................] - ETA: 0s - loss: 0.0501 - accuracy: 0.9861 4224/6993 [=================>............] - ETA: 0s - loss: 0.0607 - accuracy: 0.9860 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0739 - accuracy: 0.9834 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0714 - accuracy: 0.9839 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0694 - accuracy: 0.9841 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0709 - accuracy: 0.9837 - val_loss: 0.6674 - val_accuracy: 0.9146 Epoch 107/199 128/6993 [..............................] - ETA: 0s - loss: 0.0170 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0756 - accuracy: 0.9877 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0714 - accuracy: 0.9850 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0679 - accuracy: 0.9860 3200/6993 [============>.................] - ETA: 0s - loss: 0.0838 - accuracy: 0.9850 4096/6993 [================>.............] - ETA: 0s - loss: 0.0794 - accuracy: 0.9854 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0735 - accuracy: 0.9854 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0661 - accuracy: 0.9863 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0753 - accuracy: 0.9844 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0771 - accuracy: 0.9840 - val_loss: 0.6118 - val_accuracy: 0.9216 Epoch 108/199 128/6993 [..............................] - ETA: 0s - loss: 0.0841 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0790 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0590 - accuracy: 0.9916 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0492 - accuracy: 0.9922 3456/6993 [=============>................] - ETA: 0s - loss: 0.0577 - accuracy: 0.9893 4352/6993 [=================>............] - ETA: 0s - loss: 0.0557 - accuracy: 0.9878 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0545 - accuracy: 0.9875 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0554 - accuracy: 0.9864 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0546 - accuracy: 0.9860 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0531 - accuracy: 0.9863 - val_loss: 0.5927 - val_accuracy: 0.9232 Epoch 109/199 128/6993 [..............................] - ETA: 0s - loss: 0.2132 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.2324 - accuracy: 0.9810 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1666 - accuracy: 0.9826 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1486 - accuracy: 0.9807 3200/6993 [============>.................] - ETA: 0s - loss: 0.1227 - accuracy: 0.9816 3968/6993 [================>.............] - ETA: 0s - loss: 0.1158 - accuracy: 0.9829 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1045 - accuracy: 0.9833 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0963 - accuracy: 0.9837 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0933 - accuracy: 0.9828 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0931 - accuracy: 0.9836 - val_loss: 0.5307 - val_accuracy: 0.9297 Epoch 110/199 128/6993 [..............................] - ETA: 0s - loss: 0.0048 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9877 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0472 - accuracy: 0.9910 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0555 - accuracy: 0.9889 3328/6993 [=============>................] - ETA: 0s - loss: 0.0433 - accuracy: 0.9913 4096/6993 [================>.............] - ETA: 0s - loss: 0.0421 - accuracy: 0.9912 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0521 - accuracy: 0.9898 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0564 - accuracy: 0.9894 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0562 - accuracy: 0.9885 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0557 - accuracy: 0.9886 - val_loss: 0.5630 - val_accuracy: 0.9257 Epoch 111/199 128/6993 [..............................] - ETA: 0s - loss: 0.0499 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0531 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0514 - accuracy: 0.9856 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0511 - accuracy: 0.9877 3200/6993 [============>.................] - ETA: 0s - loss: 0.0573 - accuracy: 0.9869 3968/6993 [================>.............] - ETA: 0s - loss: 0.0555 - accuracy: 0.9864 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0564 - accuracy: 0.9856 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0509 - accuracy: 0.9872 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0484 - accuracy: 0.9877 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0529 - accuracy: 0.9868 - val_loss: 0.6587 - val_accuracy: 0.9196 Epoch 112/199 128/6993 [..............................] - ETA: 0s - loss: 0.0472 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0544 - accuracy: 0.9873 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0535 - accuracy: 0.9877 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0488 - accuracy: 0.9896 3456/6993 [=============>................] - ETA: 0s - loss: 0.0461 - accuracy: 0.9896 4224/6993 [=================>............] - ETA: 0s - loss: 0.0587 - accuracy: 0.9877 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0613 - accuracy: 0.9867 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0617 - accuracy: 0.9862 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0611 - accuracy: 0.9865 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0615 - accuracy: 0.9864 - val_loss: 0.5880 - val_accuracy: 0.9297 Epoch 113/199 128/6993 [..............................] - ETA: 0s - loss: 0.0832 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.1018 - accuracy: 0.9777 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0944 - accuracy: 0.9802 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1076 - accuracy: 0.9809 3328/6993 [=============>................] - ETA: 0s - loss: 0.1018 - accuracy: 0.9802 3968/6993 [================>.............] - ETA: 0s - loss: 0.0975 - accuracy: 0.9811 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0930 - accuracy: 0.9821 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1020 - accuracy: 0.9816 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1004 - accuracy: 0.9814 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0942 - accuracy: 0.9818 6993/6993 [==============================] - 1s 102us/sample - loss: 0.0934 - accuracy: 0.9820 - val_loss: 0.5429 - val_accuracy: 0.9221 Epoch 114/199 128/6993 [..............................] - ETA: 0s - loss: 0.0368 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.0603 - accuracy: 0.9922 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0631 - accuracy: 0.9887 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0506 - accuracy: 0.9898 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0464 - accuracy: 0.9894 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0488 - accuracy: 0.9893 3456/6993 [=============>................] - ETA: 0s - loss: 0.0496 - accuracy: 0.9881 4096/6993 [================>.............] - ETA: 0s - loss: 0.0480 - accuracy: 0.9878 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0477 - accuracy: 0.9875 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0513 - accuracy: 0.9876 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0512 - accuracy: 0.9877 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0519 - accuracy: 0.9877 - val_loss: 0.7051 - val_accuracy: 0.9171 Epoch 115/199 128/6993 [..............................] - ETA: 0s - loss: 0.0446 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0717 - accuracy: 0.9863 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0892 - accuracy: 0.9839 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0864 - accuracy: 0.9847 3456/6993 [=============>................] - ETA: 0s - loss: 0.0833 - accuracy: 0.9835 4224/6993 [=================>............] - ETA: 0s - loss: 0.0789 - accuracy: 0.9839 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0827 - accuracy: 0.9838 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0816 - accuracy: 0.9853 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0768 - accuracy: 0.9858 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0755 - accuracy: 0.9860 - val_loss: 0.4999 - val_accuracy: 0.9272 Epoch 116/199 128/6993 [..............................] - ETA: 0s - loss: 0.0029 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0473 - accuracy: 0.9870 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0346 - accuracy: 0.9909 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0288 - accuracy: 0.9917 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0315 - accuracy: 0.9898 3456/6993 [=============>................] - ETA: 0s - loss: 0.0392 - accuracy: 0.9896 4224/6993 [=================>............] - ETA: 0s - loss: 0.0432 - accuracy: 0.9901 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0626 - accuracy: 0.9892 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0616 - accuracy: 0.9894 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0611 - accuracy: 0.9891 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0645 - accuracy: 0.9887 - val_loss: 0.6653 - val_accuracy: 0.9252 Epoch 117/199 128/6993 [..............................] - ETA: 0s - loss: 0.1938 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0763 - accuracy: 0.9805 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0873 - accuracy: 0.9837 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0800 - accuracy: 0.9839 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0799 - accuracy: 0.9857 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0779 - accuracy: 0.9855 4352/6993 [=================>............] - ETA: 0s - loss: 0.0808 - accuracy: 0.9848 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0775 - accuracy: 0.9848 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0737 - accuracy: 0.9857 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0787 - accuracy: 0.9842 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0785 - accuracy: 0.9844 - val_loss: 0.5657 - val_accuracy: 0.9237 Epoch 118/199 128/6993 [..............................] - ETA: 0s - loss: 0.1762 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.1107 - accuracy: 0.9866 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0894 - accuracy: 0.9870 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0822 - accuracy: 0.9897 3200/6993 [============>.................] - ETA: 0s - loss: 0.0907 - accuracy: 0.9881 4096/6993 [================>.............] - ETA: 0s - loss: 0.0815 - accuracy: 0.9883 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0762 - accuracy: 0.9886 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0729 - accuracy: 0.9887 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0734 - accuracy: 0.9886 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0728 - accuracy: 0.9887 - val_loss: 0.5709 - val_accuracy: 0.9242 Epoch 119/199 128/6993 [..............................] - ETA: 0s - loss: 0.0398 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0483 - accuracy: 0.9941 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0638 - accuracy: 0.9865 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0615 - accuracy: 0.9877 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0537 - accuracy: 0.9886 4352/6993 [=================>............] - ETA: 0s - loss: 0.0531 - accuracy: 0.9878 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0513 - accuracy: 0.9887 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0491 - accuracy: 0.9887 6784/6993 [============================>.] - ETA: 0s - loss: 0.0502 - accuracy: 0.9885 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0494 - accuracy: 0.9887 - val_loss: 0.6368 - val_accuracy: 0.9312 Epoch 120/199 128/6993 [..............................] - ETA: 0s - loss: 0.1001 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0464 - accuracy: 0.9896 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0693 - accuracy: 0.9883 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0641 - accuracy: 0.9887 3200/6993 [============>.................] - ETA: 0s - loss: 0.0647 - accuracy: 0.9875 3968/6993 [================>.............] - ETA: 0s - loss: 0.0621 - accuracy: 0.9871 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0569 - accuracy: 0.9881 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0576 - accuracy: 0.9885 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0622 - accuracy: 0.9881 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0616 - accuracy: 0.9883 - val_loss: 0.5730 - val_accuracy: 0.9267 Epoch 121/199 128/6993 [..............................] - ETA: 0s - loss: 0.0544 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1036 - accuracy: 0.9824 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0764 - accuracy: 0.9838 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0597 - accuracy: 0.9866 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0877 - accuracy: 0.9838 4352/6993 [=================>............] - ETA: 0s - loss: 0.0783 - accuracy: 0.9853 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0828 - accuracy: 0.9855 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0802 - accuracy: 0.9852 6784/6993 [============================>.] - ETA: 0s - loss: 0.0778 - accuracy: 0.9856 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0759 - accuracy: 0.9860 - val_loss: 0.5731 - val_accuracy: 0.9262 Epoch 122/199 128/6993 [..............................] - ETA: 0s - loss: 0.0083 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0487 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0739 - accuracy: 0.9844 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0651 - accuracy: 0.9856 3200/6993 [============>.................] - ETA: 0s - loss: 0.0743 - accuracy: 0.9847 3968/6993 [================>.............] - ETA: 0s - loss: 0.0627 - accuracy: 0.9864 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0591 - accuracy: 0.9873 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0604 - accuracy: 0.9867 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0651 - accuracy: 0.9867 6784/6993 [============================>.] - ETA: 0s - loss: 0.0683 - accuracy: 0.9863 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0668 - accuracy: 0.9863 - val_loss: 0.5713 - val_accuracy: 0.9211 Epoch 123/199 128/6993 [..............................] - ETA: 0s - loss: 0.0362 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0517 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0705 - accuracy: 0.9865 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0638 - accuracy: 0.9881 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0572 - accuracy: 0.9883 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0819 - accuracy: 0.9873 4352/6993 [=================>............] - ETA: 0s - loss: 0.0739 - accuracy: 0.9878 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0754 - accuracy: 0.9869 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0705 - accuracy: 0.9874 6912/6993 [============================>.] - ETA: 0s - loss: 0.0713 - accuracy: 0.9876 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0705 - accuracy: 0.9877 - val_loss: 0.5575 - val_accuracy: 0.9242 Epoch 124/199 128/6993 [..............................] - ETA: 0s - loss: 0.0034 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0815 - accuracy: 0.9821 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0826 - accuracy: 0.9826 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0968 - accuracy: 0.9840 3456/6993 [=============>................] - ETA: 0s - loss: 0.0872 - accuracy: 0.9850 4096/6993 [================>.............] - ETA: 0s - loss: 0.0864 - accuracy: 0.9844 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0840 - accuracy: 0.9844 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0797 - accuracy: 0.9852 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0759 - accuracy: 0.9863 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0767 - accuracy: 0.9860 - val_loss: 0.5766 - val_accuracy: 0.9221 Epoch 125/199 128/6993 [..............................] - ETA: 0s - loss: 0.0394 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0184 - accuracy: 0.9932 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0632 - accuracy: 0.9860 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0674 - accuracy: 0.9851 3456/6993 [=============>................] - ETA: 0s - loss: 0.0684 - accuracy: 0.9838 4096/6993 [================>.............] - ETA: 0s - loss: 0.0624 - accuracy: 0.9849 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0605 - accuracy: 0.9860 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0608 - accuracy: 0.9861 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0647 - accuracy: 0.9857 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0643 - accuracy: 0.9856 - val_loss: 0.6813 - val_accuracy: 0.9151 Epoch 126/199 128/6993 [..............................] - ETA: 0s - loss: 0.1539 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.0765 - accuracy: 0.9821 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0583 - accuracy: 0.9894 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0496 - accuracy: 0.9906 3328/6993 [=============>................] - ETA: 0s - loss: 0.0494 - accuracy: 0.9904 4096/6993 [================>.............] - ETA: 0s - loss: 0.0523 - accuracy: 0.9912 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0570 - accuracy: 0.9903 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0510 - accuracy: 0.9915 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0506 - accuracy: 0.9913 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0501 - accuracy: 0.9913 - val_loss: 0.6128 - val_accuracy: 0.9272 Epoch 127/199 128/6993 [..............................] - ETA: 0s - loss: 0.1439 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0621 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0821 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0842 - accuracy: 0.9852 3328/6993 [=============>................] - ETA: 0s - loss: 0.0760 - accuracy: 0.9862 4224/6993 [=================>............] - ETA: 0s - loss: 0.0704 - accuracy: 0.9870 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0662 - accuracy: 0.9864 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0638 - accuracy: 0.9869 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0666 - accuracy: 0.9868 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0656 - accuracy: 0.9870 - val_loss: 0.6448 - val_accuracy: 0.9262 Epoch 128/199 128/6993 [..............................] - ETA: 0s - loss: 0.0178 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0357 - accuracy: 0.9941 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0351 - accuracy: 0.9916 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0428 - accuracy: 0.9901 3200/6993 [============>.................] - ETA: 0s - loss: 0.0498 - accuracy: 0.9894 4096/6993 [================>.............] - ETA: 0s - loss: 0.0436 - accuracy: 0.9895 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0579 - accuracy: 0.9882 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0586 - accuracy: 0.9875 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0551 - accuracy: 0.9880 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0570 - accuracy: 0.9878 - val_loss: 0.6490 - val_accuracy: 0.9252 Epoch 129/199 128/6993 [..............................] - ETA: 0s - loss: 0.0075 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0438 - accuracy: 0.9900 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0702 - accuracy: 0.9870 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0556 - accuracy: 0.9887 3072/6993 [============>.................] - ETA: 0s - loss: 0.0636 - accuracy: 0.9896 3968/6993 [================>.............] - ETA: 0s - loss: 0.0571 - accuracy: 0.9904 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0590 - accuracy: 0.9891 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0605 - accuracy: 0.9893 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0681 - accuracy: 0.9873 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0771 - accuracy: 0.9861 - val_loss: 0.5773 - val_accuracy: 0.9216 Epoch 130/199 128/6993 [..............................] - ETA: 0s - loss: 0.0215 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0411 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0803 - accuracy: 0.9872 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0886 - accuracy: 0.9836 3328/6993 [=============>................] - ETA: 0s - loss: 0.0792 - accuracy: 0.9850 3968/6993 [================>.............] - ETA: 0s - loss: 0.0926 - accuracy: 0.9844 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0922 - accuracy: 0.9837 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0917 - accuracy: 0.9827 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0876 - accuracy: 0.9834 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0888 - accuracy: 0.9830 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0863 - accuracy: 0.9834 - val_loss: 0.5838 - val_accuracy: 0.9262 Epoch 131/199 128/6993 [..............................] - ETA: 0s - loss: 0.0319 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0268 - accuracy: 0.9948 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0521 - accuracy: 0.9908 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0492 - accuracy: 0.9893 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0483 - accuracy: 0.9890 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0572 - accuracy: 0.9880 4352/6993 [=================>............] - ETA: 0s - loss: 0.0625 - accuracy: 0.9883 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0612 - accuracy: 0.9876 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0599 - accuracy: 0.9867 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0641 - accuracy: 0.9863 6912/6993 [============================>.] - ETA: 0s - loss: 0.0696 - accuracy: 0.9858 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0691 - accuracy: 0.9858 - val_loss: 0.5953 - val_accuracy: 0.9232 Epoch 132/199 128/6993 [..............................] - ETA: 0s - loss: 0.1862 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0956 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0788 - accuracy: 0.9844 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0726 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0645 - accuracy: 0.9855 3200/6993 [============>.................] - ETA: 0s - loss: 0.0554 - accuracy: 0.9872 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0483 - accuracy: 0.9891 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0568 - accuracy: 0.9879 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0545 - accuracy: 0.9879 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0605 - accuracy: 0.9866 6912/6993 [============================>.] - ETA: 0s - loss: 0.0597 - accuracy: 0.9870 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0600 - accuracy: 0.9868 - val_loss: 0.7595 - val_accuracy: 0.9226 Epoch 133/199 128/6993 [..............................] - ETA: 0s - loss: 0.0277 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0885 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0795 - accuracy: 0.9858 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0739 - accuracy: 0.9858 3072/6993 [============>.................] - ETA: 0s - loss: 0.0715 - accuracy: 0.9854 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0754 - accuracy: 0.9859 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0840 - accuracy: 0.9850 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0796 - accuracy: 0.9856 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0825 - accuracy: 0.9859 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0800 - accuracy: 0.9860 - val_loss: 0.6969 - val_accuracy: 0.9242 Epoch 134/199 128/6993 [..............................] - ETA: 0s - loss: 0.0477 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0807 - accuracy: 0.9854 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0581 - accuracy: 0.9872 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0483 - accuracy: 0.9885 3456/6993 [=============>................] - ETA: 0s - loss: 0.0403 - accuracy: 0.9902 4352/6993 [=================>............] - ETA: 0s - loss: 0.0442 - accuracy: 0.9892 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0451 - accuracy: 0.9894 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0476 - accuracy: 0.9885 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0545 - accuracy: 0.9875 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0535 - accuracy: 0.9878 - val_loss: 0.6863 - val_accuracy: 0.9226 Epoch 135/199 128/6993 [..............................] - ETA: 0s - loss: 0.0714 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0684 - accuracy: 0.9799 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1052 - accuracy: 0.9810 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0813 - accuracy: 0.9840 3456/6993 [=============>................] - ETA: 0s - loss: 0.0952 - accuracy: 0.9823 4224/6993 [=================>............] - ETA: 0s - loss: 0.0894 - accuracy: 0.9825 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0886 - accuracy: 0.9838 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0880 - accuracy: 0.9837 6784/6993 [============================>.] - ETA: 0s - loss: 0.0847 - accuracy: 0.9848 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0823 - accuracy: 0.9853 - val_loss: 0.5884 - val_accuracy: 0.9333 Epoch 136/199 128/6993 [..............................] - ETA: 0s - loss: 0.0100 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.1300 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0999 - accuracy: 0.9898 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0889 - accuracy: 0.9881 3328/6993 [=============>................] - ETA: 0s - loss: 0.0817 - accuracy: 0.9868 4096/6993 [================>.............] - ETA: 0s - loss: 0.0752 - accuracy: 0.9866 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0728 - accuracy: 0.9864 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0746 - accuracy: 0.9866 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0691 - accuracy: 0.9869 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0692 - accuracy: 0.9871 - val_loss: 0.6157 - val_accuracy: 0.9211 Epoch 137/199 128/6993 [..............................] - ETA: 0s - loss: 0.0967 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0384 - accuracy: 0.9866 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0415 - accuracy: 0.9863 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0525 - accuracy: 0.9839 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0507 - accuracy: 0.9862 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0540 - accuracy: 0.9863 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0573 - accuracy: 0.9855 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0555 - accuracy: 0.9863 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0533 - accuracy: 0.9871 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0534 - accuracy: 0.9876 - val_loss: 0.6919 - val_accuracy: 0.9262 Epoch 138/199 128/6993 [..............................] - ETA: 0s - loss: 0.0654 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1127 - accuracy: 0.9863 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1028 - accuracy: 0.9868 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0966 - accuracy: 0.9844 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0798 - accuracy: 0.9861 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0796 - accuracy: 0.9855 4224/6993 [=================>............] - ETA: 0s - loss: 0.0795 - accuracy: 0.9858 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0832 - accuracy: 0.9858 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0833 - accuracy: 0.9862 6784/6993 [============================>.] - ETA: 0s - loss: 0.0813 - accuracy: 0.9867 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0794 - accuracy: 0.9868 - val_loss: 0.6509 - val_accuracy: 0.9211 Epoch 139/199 128/6993 [..............................] - ETA: 0s - loss: 0.0329 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1209 - accuracy: 0.9818 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0708 - accuracy: 0.9876 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0621 - accuracy: 0.9881 3328/6993 [=============>................] - ETA: 0s - loss: 0.0623 - accuracy: 0.9880 4096/6993 [================>.............] - ETA: 0s - loss: 0.0568 - accuracy: 0.9885 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0627 - accuracy: 0.9868 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0614 - accuracy: 0.9861 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0640 - accuracy: 0.9863 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0664 - accuracy: 0.9861 - val_loss: 0.6301 - val_accuracy: 0.9135 Epoch 140/199 128/6993 [..............................] - ETA: 1s - loss: 0.0567 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0255 - accuracy: 0.9912 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0231 - accuracy: 0.9939 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0284 - accuracy: 0.9929 3456/6993 [=============>................] - ETA: 0s - loss: 0.0461 - accuracy: 0.9896 4224/6993 [=================>............] - ETA: 0s - loss: 0.0472 - accuracy: 0.9891 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0489 - accuracy: 0.9890 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0532 - accuracy: 0.9885 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0620 - accuracy: 0.9875 6912/6993 [============================>.] - ETA: 0s - loss: 0.0658 - accuracy: 0.9873 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0653 - accuracy: 0.9873 - val_loss: 0.6186 - val_accuracy: 0.9201 Epoch 141/199 128/6993 [..............................] - ETA: 0s - loss: 0.0169 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0420 - accuracy: 0.9922 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0293 - accuracy: 0.9934 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0385 - accuracy: 0.9918 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0455 - accuracy: 0.9912 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0478 - accuracy: 0.9905 4224/6993 [=================>............] - ETA: 0s - loss: 0.0481 - accuracy: 0.9905 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0513 - accuracy: 0.9901 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0529 - accuracy: 0.9892 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0530 - accuracy: 0.9887 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0520 - accuracy: 0.9884 - val_loss: 0.6571 - val_accuracy: 0.9247 Epoch 142/199 128/6993 [..............................] - ETA: 0s - loss: 0.3634 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1810 - accuracy: 0.9877 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1267 - accuracy: 0.9862 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1075 - accuracy: 0.9859 3456/6993 [=============>................] - ETA: 0s - loss: 0.1007 - accuracy: 0.9829 4224/6993 [=================>............] - ETA: 0s - loss: 0.1012 - accuracy: 0.9832 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0957 - accuracy: 0.9838 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0925 - accuracy: 0.9837 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0921 - accuracy: 0.9844 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0910 - accuracy: 0.9841 - val_loss: 0.5246 - val_accuracy: 0.9317 Epoch 143/199 128/6993 [..............................] - ETA: 0s - loss: 0.0053 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0535 - accuracy: 0.9932 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0482 - accuracy: 0.9917 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0508 - accuracy: 0.9903 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0563 - accuracy: 0.9888 4224/6993 [=================>............] - ETA: 0s - loss: 0.0536 - accuracy: 0.9893 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0485 - accuracy: 0.9895 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0567 - accuracy: 0.9890 6784/6993 [============================>.] - ETA: 0s - loss: 0.0596 - accuracy: 0.9882 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0600 - accuracy: 0.9880 - val_loss: 0.7529 - val_accuracy: 0.9196 Epoch 144/199 128/6993 [..............................] - ETA: 0s - loss: 0.0440 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0712 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0805 - accuracy: 0.9838 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0663 - accuracy: 0.9863 3456/6993 [=============>................] - ETA: 0s - loss: 0.0703 - accuracy: 0.9870 4096/6993 [================>.............] - ETA: 0s - loss: 0.0632 - accuracy: 0.9878 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0650 - accuracy: 0.9882 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0725 - accuracy: 0.9878 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0743 - accuracy: 0.9871 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0756 - accuracy: 0.9871 - val_loss: 0.6782 - val_accuracy: 0.9267 Epoch 145/199 128/6993 [..............................] - ETA: 0s - loss: 0.1492 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0589 - accuracy: 0.9912 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0631 - accuracy: 0.9892 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0491 - accuracy: 0.9906 3328/6993 [=============>................] - ETA: 0s - loss: 0.0584 - accuracy: 0.9886 4096/6993 [================>.............] - ETA: 0s - loss: 0.0549 - accuracy: 0.9890 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0561 - accuracy: 0.9892 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0544 - accuracy: 0.9898 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0563 - accuracy: 0.9884 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0578 - accuracy: 0.9876 - val_loss: 0.6597 - val_accuracy: 0.9196 Epoch 146/199 128/6993 [..............................] - ETA: 0s - loss: 0.0743 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0933 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0671 - accuracy: 0.9900 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0784 - accuracy: 0.9877 3328/6993 [=============>................] - ETA: 0s - loss: 0.0728 - accuracy: 0.9874 4096/6993 [================>.............] - ETA: 0s - loss: 0.0718 - accuracy: 0.9866 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0806 - accuracy: 0.9856 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0721 - accuracy: 0.9865 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0719 - accuracy: 0.9859 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0707 - accuracy: 0.9860 - val_loss: 0.7249 - val_accuracy: 0.9201 Epoch 147/199 128/6993 [..............................] - ETA: 0s - loss: 0.0279 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0334 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0573 - accuracy: 0.9894 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0534 - accuracy: 0.9889 3200/6993 [============>.................] - ETA: 0s - loss: 0.0965 - accuracy: 0.9866 3968/6993 [================>.............] - ETA: 0s - loss: 0.0915 - accuracy: 0.9861 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0824 - accuracy: 0.9870 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0865 - accuracy: 0.9874 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0829 - accuracy: 0.9867 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0849 - accuracy: 0.9860 - val_loss: 0.6988 - val_accuracy: 0.9186 Epoch 148/199 128/6993 [..............................] - ETA: 0s - loss: 0.3047 - accuracy: 0.9609 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0960 - accuracy: 0.9863 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0733 - accuracy: 0.9872 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0810 - accuracy: 0.9867 3456/6993 [=============>................] - ETA: 0s - loss: 0.0771 - accuracy: 0.9873 4224/6993 [=================>............] - ETA: 0s - loss: 0.0664 - accuracy: 0.9879 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0623 - accuracy: 0.9883 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0631 - accuracy: 0.9888 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0601 - accuracy: 0.9889 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0580 - accuracy: 0.9891 - val_loss: 0.6310 - val_accuracy: 0.9287 Epoch 149/199 128/6993 [..............................] - ETA: 0s - loss: 0.0027 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0581 - accuracy: 0.9824 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0856 - accuracy: 0.9820 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0733 - accuracy: 0.9836 3328/6993 [=============>................] - ETA: 0s - loss: 0.0678 - accuracy: 0.9847 4096/6993 [================>.............] - ETA: 0s - loss: 0.0655 - accuracy: 0.9846 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0581 - accuracy: 0.9862 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0584 - accuracy: 0.9867 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0559 - accuracy: 0.9866 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0576 - accuracy: 0.9857 - val_loss: 0.7098 - val_accuracy: 0.9221 Epoch 150/199 128/6993 [..............................] - ETA: 0s - loss: 0.1859 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.1235 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0839 - accuracy: 0.9858 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0919 - accuracy: 0.9821 3072/6993 [============>.................] - ETA: 0s - loss: 0.0838 - accuracy: 0.9834 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0938 - accuracy: 0.9830 4352/6993 [=================>............] - ETA: 0s - loss: 0.0877 - accuracy: 0.9832 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0850 - accuracy: 0.9840 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0832 - accuracy: 0.9835 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0927 - accuracy: 0.9831 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0965 - accuracy: 0.9826 - val_loss: 0.5751 - val_accuracy: 0.9247 Epoch 151/199 128/6993 [..............................] - ETA: 0s - loss: 0.0308 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0695 - accuracy: 0.9873 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0709 - accuracy: 0.9875 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9854 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0627 - accuracy: 0.9863 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0649 - accuracy: 0.9857 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0622 - accuracy: 0.9860 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0620 - accuracy: 0.9865 6912/6993 [============================>.] - ETA: 0s - loss: 0.0588 - accuracy: 0.9868 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0602 - accuracy: 0.9867 - val_loss: 0.6131 - val_accuracy: 0.9312 Epoch 152/199 128/6993 [..............................] - ETA: 0s - loss: 0.0306 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0490 - accuracy: 0.9873 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0439 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0379 - accuracy: 0.9911 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0333 - accuracy: 0.9925 4352/6993 [=================>............] - ETA: 0s - loss: 0.0468 - accuracy: 0.9903 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0546 - accuracy: 0.9888 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0549 - accuracy: 0.9889 6912/6993 [============================>.] - ETA: 0s - loss: 0.0515 - accuracy: 0.9896 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0522 - accuracy: 0.9896 - val_loss: 0.6806 - val_accuracy: 0.9323 Epoch 153/199 128/6993 [..............................] - ETA: 0s - loss: 0.0576 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1241 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1190 - accuracy: 0.9872 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1112 - accuracy: 0.9866 3456/6993 [=============>................] - ETA: 0s - loss: 0.1102 - accuracy: 0.9850 4352/6993 [=================>............] - ETA: 0s - loss: 0.1012 - accuracy: 0.9851 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0977 - accuracy: 0.9852 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0907 - accuracy: 0.9857 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0882 - accuracy: 0.9853 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0856 - accuracy: 0.9856 - val_loss: 0.5713 - val_accuracy: 0.9262 Epoch 154/199 128/6993 [..............................] - ETA: 0s - loss: 0.0259 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0543 - accuracy: 0.9902 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0571 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0469 - accuracy: 0.9888 3456/6993 [=============>................] - ETA: 0s - loss: 0.0612 - accuracy: 0.9870 4352/6993 [=================>............] - ETA: 0s - loss: 0.0589 - accuracy: 0.9869 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0552 - accuracy: 0.9873 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0530 - accuracy: 0.9877 6784/6993 [============================>.] - ETA: 0s - loss: 0.0522 - accuracy: 0.9882 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0517 - accuracy: 0.9884 - val_loss: 0.6710 - val_accuracy: 0.9257 Epoch 155/199 128/6993 [..............................] - ETA: 0s - loss: 0.0901 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0424 - accuracy: 0.9902 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0522 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0481 - accuracy: 0.9900 3456/6993 [=============>................] - ETA: 0s - loss: 0.0494 - accuracy: 0.9893 4096/6993 [================>.............] - ETA: 0s - loss: 0.0543 - accuracy: 0.9883 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0545 - accuracy: 0.9884 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0596 - accuracy: 0.9884 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0618 - accuracy: 0.9881 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0629 - accuracy: 0.9884 - val_loss: 0.6351 - val_accuracy: 0.9282 Epoch 156/199 128/6993 [..............................] - ETA: 0s - loss: 0.0147 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0484 - accuracy: 0.9912 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0565 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0727 - accuracy: 0.9866 3456/6993 [=============>................] - ETA: 0s - loss: 0.0621 - accuracy: 0.9881 4352/6993 [=================>............] - ETA: 0s - loss: 0.0640 - accuracy: 0.9876 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0745 - accuracy: 0.9878 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0828 - accuracy: 0.9869 6912/6993 [============================>.] - ETA: 0s - loss: 0.0814 - accuracy: 0.9868 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0810 - accuracy: 0.9868 - val_loss: 0.5831 - val_accuracy: 0.9317 Epoch 157/199 128/6993 [..............................] - ETA: 0s - loss: 0.0322 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0548 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0672 - accuracy: 0.9874 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0617 - accuracy: 0.9871 3200/6993 [============>.................] - ETA: 0s - loss: 0.0616 - accuracy: 0.9878 3968/6993 [================>.............] - ETA: 0s - loss: 0.0577 - accuracy: 0.9882 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0777 - accuracy: 0.9881 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0822 - accuracy: 0.9869 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0849 - accuracy: 0.9868 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0881 - accuracy: 0.9863 - val_loss: 0.6353 - val_accuracy: 0.9242 Epoch 158/199 128/6993 [..............................] - ETA: 0s - loss: 0.0909 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0835 - accuracy: 0.9833 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0695 - accuracy: 0.9880 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0503 - accuracy: 0.9906 3328/6993 [=============>................] - ETA: 0s - loss: 0.0521 - accuracy: 0.9892 4224/6993 [=================>............] - ETA: 0s - loss: 0.0502 - accuracy: 0.9886 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0497 - accuracy: 0.9889 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0491 - accuracy: 0.9886 6784/6993 [============================>.] - ETA: 0s - loss: 0.0503 - accuracy: 0.9889 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0491 - accuracy: 0.9891 - val_loss: 0.6845 - val_accuracy: 0.9287 Epoch 159/199 128/6993 [..............................] - ETA: 0s - loss: 0.0549 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0432 - accuracy: 0.9933 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0352 - accuracy: 0.9915 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0380 - accuracy: 0.9913 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0425 - accuracy: 0.9901 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0542 - accuracy: 0.9888 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0553 - accuracy: 0.9893 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0563 - accuracy: 0.9898 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0594 - accuracy: 0.9888 6912/6993 [============================>.] - ETA: 0s - loss: 0.0680 - accuracy: 0.9886 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0676 - accuracy: 0.9884 - val_loss: 0.6317 - val_accuracy: 0.9282 Epoch 160/199 128/6993 [..............................] - ETA: 0s - loss: 0.1347 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0606 - accuracy: 0.9937 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0416 - accuracy: 0.9945 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0617 - accuracy: 0.9905 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0702 - accuracy: 0.9891 3072/6993 [============>.................] - ETA: 0s - loss: 0.0637 - accuracy: 0.9896 3968/6993 [================>.............] - ETA: 0s - loss: 0.0541 - accuracy: 0.9907 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0486 - accuracy: 0.9910 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0510 - accuracy: 0.9903 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0589 - accuracy: 0.9893 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0587 - accuracy: 0.9893 - val_loss: 0.6652 - val_accuracy: 0.9242 Epoch 161/199 128/6993 [..............................] - ETA: 0s - loss: 0.0027 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0652 - accuracy: 0.9883 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0498 - accuracy: 0.9910 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0478 - accuracy: 0.9914 3328/6993 [=============>................] - ETA: 0s - loss: 0.0504 - accuracy: 0.9895 4096/6993 [================>.............] - ETA: 0s - loss: 0.0467 - accuracy: 0.9900 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0528 - accuracy: 0.9894 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0567 - accuracy: 0.9891 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0559 - accuracy: 0.9889 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0678 - accuracy: 0.9888 - val_loss: 0.7280 - val_accuracy: 0.9312 Epoch 162/199 128/6993 [..............................] - ETA: 0s - loss: 9.9308e-04 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0321 - accuracy: 0.9900 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0390 - accuracy: 0.9905 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0364 - accuracy: 0.9896 3456/6993 [=============>................] - ETA: 0s - loss: 0.0412 - accuracy: 0.9905 4352/6993 [=================>............] - ETA: 0s - loss: 0.0546 - accuracy: 0.9897 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0577 - accuracy: 0.9887 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0665 - accuracy: 0.9884 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0670 - accuracy: 0.9880 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0661 - accuracy: 0.9880 - val_loss: 0.6421 - val_accuracy: 0.9252 Epoch 163/199 128/6993 [..............................] - ETA: 0s - loss: 0.0123 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0253 - accuracy: 0.9933 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0363 - accuracy: 0.9904 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0300 - accuracy: 0.9926 3328/6993 [=============>................] - ETA: 0s - loss: 0.0299 - accuracy: 0.9922 4224/6993 [=================>............] - ETA: 0s - loss: 0.0407 - accuracy: 0.9915 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0398 - accuracy: 0.9912 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0398 - accuracy: 0.9909 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0488 - accuracy: 0.9890 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0568 - accuracy: 0.9886 - val_loss: 0.7761 - val_accuracy: 0.9257 Epoch 164/199 128/6993 [..............................] - ETA: 0s - loss: 0.0321 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0864 - accuracy: 0.9912 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0834 - accuracy: 0.9877 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0785 - accuracy: 0.9888 3456/6993 [=============>................] - ETA: 0s - loss: 0.0778 - accuracy: 0.9881 4096/6993 [================>.............] - ETA: 0s - loss: 0.0750 - accuracy: 0.9880 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0707 - accuracy: 0.9881 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0763 - accuracy: 0.9869 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0721 - accuracy: 0.9869 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0691 - accuracy: 0.9871 - val_loss: 0.6323 - val_accuracy: 0.9287 Epoch 165/199 128/6993 [..............................] - ETA: 0s - loss: 0.0282 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0594 - accuracy: 0.9922 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0605 - accuracy: 0.9896 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0589 - accuracy: 0.9892 3456/6993 [=============>................] - ETA: 0s - loss: 0.0729 - accuracy: 0.9870 4352/6993 [=================>............] - ETA: 0s - loss: 0.0710 - accuracy: 0.9869 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0646 - accuracy: 0.9872 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0618 - accuracy: 0.9877 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0605 - accuracy: 0.9883 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0595 - accuracy: 0.9884 - val_loss: 0.7017 - val_accuracy: 0.9312 Epoch 166/199 128/6993 [..............................] - ETA: 0s - loss: 0.0572 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0472 - accuracy: 0.9877 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0700 - accuracy: 0.9857 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0689 - accuracy: 0.9877 3328/6993 [=============>................] - ETA: 0s - loss: 0.0803 - accuracy: 0.9877 3968/6993 [================>.............] - ETA: 0s - loss: 0.0769 - accuracy: 0.9879 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0682 - accuracy: 0.9882 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0669 - accuracy: 0.9880 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0620 - accuracy: 0.9887 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0617 - accuracy: 0.9890 - val_loss: 0.6715 - val_accuracy: 0.9307 Epoch 167/199 128/6993 [..............................] - ETA: 0s - loss: 7.1147e-05 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0844 - accuracy: 0.9855 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1160 - accuracy: 0.9808 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0829 - accuracy: 0.9852 3456/6993 [=============>................] - ETA: 0s - loss: 0.0728 - accuracy: 0.9870 4224/6993 [=================>............] - ETA: 0s - loss: 0.0634 - accuracy: 0.9882 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0677 - accuracy: 0.9882 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0820 - accuracy: 0.9873 6784/6993 [============================>.] - ETA: 0s - loss: 0.0800 - accuracy: 0.9875 6993/6993 [==============================] - 1s 77us/sample - loss: 0.0822 - accuracy: 0.9870 - val_loss: 0.6667 - val_accuracy: 0.9166 Epoch 168/199 128/6993 [..............................] - ETA: 0s - loss: 0.1167 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0360 - accuracy: 0.9922 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0310 - accuracy: 0.9922 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0342 - accuracy: 0.9905 3072/6993 [============>.................] - ETA: 0s - loss: 0.0364 - accuracy: 0.9912 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0369 - accuracy: 0.9916 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0480 - accuracy: 0.9904 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0442 - accuracy: 0.9910 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0453 - accuracy: 0.9910 6912/6993 [============================>.] - ETA: 0s - loss: 0.0469 - accuracy: 0.9912 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0486 - accuracy: 0.9911 - val_loss: 0.7548 - val_accuracy: 0.9186 Epoch 169/199 128/6993 [..............................] - ETA: 0s - loss: 0.0196 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0503 - accuracy: 0.9877 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0679 - accuracy: 0.9850 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0650 - accuracy: 0.9854 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0664 - accuracy: 0.9847 3456/6993 [=============>................] - ETA: 0s - loss: 0.0634 - accuracy: 0.9852 4096/6993 [================>.............] - ETA: 0s - loss: 0.0583 - accuracy: 0.9863 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0612 - accuracy: 0.9865 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0588 - accuracy: 0.9874 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0602 - accuracy: 0.9869 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0697 - accuracy: 0.9860 - val_loss: 0.6848 - val_accuracy: 0.9221 Epoch 170/199 128/6993 [..............................] - ETA: 0s - loss: 0.0102 - accuracy: 1.0000 640/6993 [=>............................] - ETA: 0s - loss: 0.0364 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0452 - accuracy: 0.9908 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0459 - accuracy: 0.9894 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0597 - accuracy: 0.9874 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0629 - accuracy: 0.9863 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0633 - accuracy: 0.9871 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0598 - accuracy: 0.9875 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0593 - accuracy: 0.9864 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0664 - accuracy: 0.9851 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0648 - accuracy: 0.9857 - val_loss: 0.7500 - val_accuracy: 0.9216 Epoch 171/199 128/6993 [..............................] - ETA: 0s - loss: 0.1069 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0861 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0756 - accuracy: 0.9874 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0711 - accuracy: 0.9895 3456/6993 [=============>................] - ETA: 0s - loss: 0.0619 - accuracy: 0.9905 4224/6993 [=================>............] - ETA: 0s - loss: 0.0588 - accuracy: 0.9903 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0511 - accuracy: 0.9910 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0482 - accuracy: 0.9912 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0515 - accuracy: 0.9907 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0498 - accuracy: 0.9907 - val_loss: 0.6734 - val_accuracy: 0.9287 Epoch 172/199 128/6993 [..............................] - ETA: 0s - loss: 0.0311 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0306 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9894 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0712 - accuracy: 0.9898 3456/6993 [=============>................] - ETA: 0s - loss: 0.0753 - accuracy: 0.9896 4352/6993 [=================>............] - ETA: 0s - loss: 0.0773 - accuracy: 0.9890 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0776 - accuracy: 0.9874 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0718 - accuracy: 0.9878 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0725 - accuracy: 0.9880 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0739 - accuracy: 0.9881 - val_loss: 0.7049 - val_accuracy: 0.9242 Epoch 173/199 128/6993 [..............................] - ETA: 0s - loss: 0.1665 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0751 - accuracy: 0.9855 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0536 - accuracy: 0.9880 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0439 - accuracy: 0.9895 3200/6993 [============>.................] - ETA: 0s - loss: 0.0522 - accuracy: 0.9887 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0607 - accuracy: 0.9883 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0695 - accuracy: 0.9873 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0692 - accuracy: 0.9871 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0754 - accuracy: 0.9870 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0737 - accuracy: 0.9871 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0720 - accuracy: 0.9873 - val_loss: 0.6156 - val_accuracy: 0.9247 Epoch 174/199 128/6993 [..............................] - ETA: 0s - loss: 0.1129 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1112 - accuracy: 0.9799 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0805 - accuracy: 0.9872 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0704 - accuracy: 0.9881 3328/6993 [=============>................] - ETA: 0s - loss: 0.0637 - accuracy: 0.9880 3968/6993 [================>.............] - ETA: 0s - loss: 0.0886 - accuracy: 0.9882 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0840 - accuracy: 0.9883 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0734 - accuracy: 0.9892 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0688 - accuracy: 0.9892 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0670 - accuracy: 0.9888 - val_loss: 0.8258 - val_accuracy: 0.9247 Epoch 175/199 128/6993 [..............................] - ETA: 0s - loss: 0.0809 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0704 - accuracy: 0.9844 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0510 - accuracy: 0.9863 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0579 - accuracy: 0.9870 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9871 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0561 - accuracy: 0.9887 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0568 - accuracy: 0.9871 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0578 - accuracy: 0.9874 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0577 - accuracy: 0.9874 6784/6993 [============================>.] - ETA: 0s - loss: 0.0629 - accuracy: 0.9872 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0624 - accuracy: 0.9870 - val_loss: 0.7148 - val_accuracy: 0.9252 Epoch 176/199 128/6993 [..............................] - ETA: 0s - loss: 0.1815 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.0791 - accuracy: 0.9859 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0902 - accuracy: 0.9859 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0770 - accuracy: 0.9871 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0708 - accuracy: 0.9871 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0761 - accuracy: 0.9865 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0715 - accuracy: 0.9865 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0661 - accuracy: 0.9874 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0605 - accuracy: 0.9881 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0621 - accuracy: 0.9883 - val_loss: 0.7054 - val_accuracy: 0.9252 Epoch 177/199 128/6993 [..............................] - ETA: 0s - loss: 0.0148 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0239 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0354 - accuracy: 0.9928 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0502 - accuracy: 0.9893 3200/6993 [============>.................] - ETA: 0s - loss: 0.0571 - accuracy: 0.9894 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0566 - accuracy: 0.9900 4352/6993 [=================>............] - ETA: 0s - loss: 0.0605 - accuracy: 0.9892 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0672 - accuracy: 0.9881 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0644 - accuracy: 0.9882 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0658 - accuracy: 0.9882 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0667 - accuracy: 0.9886 - val_loss: 0.6971 - val_accuracy: 0.9237 Epoch 178/199 128/6993 [..............................] - ETA: 0s - loss: 0.1082 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.0536 - accuracy: 0.9877 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0414 - accuracy: 0.9902 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0443 - accuracy: 0.9905 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0477 - accuracy: 0.9908 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0705 - accuracy: 0.9886 4224/6993 [=================>............] - ETA: 0s - loss: 0.0663 - accuracy: 0.9882 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0659 - accuracy: 0.9881 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0656 - accuracy: 0.9880 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0636 - accuracy: 0.9880 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0603 - accuracy: 0.9884 - val_loss: 0.7208 - val_accuracy: 0.9292 Epoch 179/199 128/6993 [..............................] - ETA: 0s - loss: 0.1946 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1219 - accuracy: 0.9710 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1054 - accuracy: 0.9772 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1044 - accuracy: 0.9815 3072/6993 [============>.................] - ETA: 0s - loss: 0.1051 - accuracy: 0.9821 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0956 - accuracy: 0.9831 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0882 - accuracy: 0.9842 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0855 - accuracy: 0.9846 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0851 - accuracy: 0.9845 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0875 - accuracy: 0.9844 - val_loss: 0.6871 - val_accuracy: 0.9282 Epoch 180/199 128/6993 [..............................] - ETA: 0s - loss: 0.0150 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0539 - accuracy: 0.9911 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0601 - accuracy: 0.9883 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0684 - accuracy: 0.9871 3456/6993 [=============>................] - ETA: 0s - loss: 0.0612 - accuracy: 0.9873 4224/6993 [=================>............] - ETA: 0s - loss: 0.0630 - accuracy: 0.9884 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0580 - accuracy: 0.9887 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0538 - accuracy: 0.9892 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0546 - accuracy: 0.9886 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0550 - accuracy: 0.9888 - val_loss: 0.7127 - val_accuracy: 0.9297 Epoch 181/199 128/6993 [..............................] - ETA: 0s - loss: 0.2637 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0643 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0912 - accuracy: 0.9900 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1002 - accuracy: 0.9883 3456/6993 [=============>................] - ETA: 0s - loss: 0.0786 - accuracy: 0.9899 4352/6993 [=================>............] - ETA: 0s - loss: 0.0983 - accuracy: 0.9892 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0906 - accuracy: 0.9888 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0816 - accuracy: 0.9888 6784/6993 [============================>.] - ETA: 0s - loss: 0.0746 - accuracy: 0.9889 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0755 - accuracy: 0.9890 - val_loss: 0.7400 - val_accuracy: 0.9317 Epoch 182/199 128/6993 [..............................] - ETA: 0s - loss: 0.0961 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0708 - accuracy: 0.9821 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0939 - accuracy: 0.9866 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0907 - accuracy: 0.9871 3456/6993 [=============>................] - ETA: 0s - loss: 0.1118 - accuracy: 0.9858 4224/6993 [=================>............] - ETA: 0s - loss: 0.0984 - accuracy: 0.9872 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0920 - accuracy: 0.9869 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0955 - accuracy: 0.9875 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0889 - accuracy: 0.9876 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0861 - accuracy: 0.9878 - val_loss: 0.6732 - val_accuracy: 0.9292 Epoch 183/199 128/6993 [..............................] - ETA: 0s - loss: 0.0057 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0648 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0751 - accuracy: 0.9900 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0684 - accuracy: 0.9914 3328/6993 [=============>................] - ETA: 0s - loss: 0.0668 - accuracy: 0.9919 4224/6993 [=================>............] - ETA: 0s - loss: 0.0642 - accuracy: 0.9908 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0671 - accuracy: 0.9903 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0637 - accuracy: 0.9906 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0671 - accuracy: 0.9897 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0651 - accuracy: 0.9897 - val_loss: 0.7039 - val_accuracy: 0.9297 Epoch 184/199 128/6993 [..............................] - ETA: 0s - loss: 0.0230 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0952 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0881 - accuracy: 0.9849 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0757 - accuracy: 0.9851 3456/6993 [=============>................] - ETA: 0s - loss: 0.0859 - accuracy: 0.9847 4352/6993 [=================>............] - ETA: 0s - loss: 0.0916 - accuracy: 0.9848 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0903 - accuracy: 0.9861 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0830 - accuracy: 0.9860 6784/6993 [============================>.] - ETA: 0s - loss: 0.0833 - accuracy: 0.9866 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0810 - accuracy: 0.9870 - val_loss: 0.7017 - val_accuracy: 0.9242 Epoch 185/199 128/6993 [..............................] - ETA: 0s - loss: 0.0762 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0441 - accuracy: 0.9870 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0682 - accuracy: 0.9857 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0613 - accuracy: 0.9862 3072/6993 [============>.................] - ETA: 0s - loss: 0.0856 - accuracy: 0.9854 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0969 - accuracy: 0.9852 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0939 - accuracy: 0.9844 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0828 - accuracy: 0.9856 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0754 - accuracy: 0.9866 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0718 - accuracy: 0.9868 - val_loss: 0.6735 - val_accuracy: 0.9307 Epoch 186/199 128/6993 [..............................] - ETA: 0s - loss: 0.0281 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0232 - accuracy: 0.9951 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0350 - accuracy: 0.9943 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0425 - accuracy: 0.9926 3328/6993 [=============>................] - ETA: 0s - loss: 0.0419 - accuracy: 0.9925 3968/6993 [================>.............] - ETA: 0s - loss: 0.0449 - accuracy: 0.9917 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0472 - accuracy: 0.9915 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0586 - accuracy: 0.9912 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0582 - accuracy: 0.9909 6784/6993 [============================>.] - ETA: 0s - loss: 0.0556 - accuracy: 0.9912 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0573 - accuracy: 0.9908 - val_loss: 0.6993 - val_accuracy: 0.9292 Epoch 187/199 128/6993 [..............................] - ETA: 0s - loss: 0.0128 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0824 - accuracy: 0.9902 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0957 - accuracy: 0.9885 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0883 - accuracy: 0.9879 3456/6993 [=============>................] - ETA: 0s - loss: 0.0749 - accuracy: 0.9884 4096/6993 [================>.............] - ETA: 0s - loss: 0.0727 - accuracy: 0.9880 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0703 - accuracy: 0.9884 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0717 - accuracy: 0.9871 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0681 - accuracy: 0.9878 6784/6993 [============================>.] - ETA: 0s - loss: 0.0630 - accuracy: 0.9885 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0634 - accuracy: 0.9880 - val_loss: 0.6626 - val_accuracy: 0.9307 Epoch 188/199 128/6993 [..............................] - ETA: 0s - loss: 0.0204 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0528 - accuracy: 0.9875 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1039 - accuracy: 0.9863 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0947 - accuracy: 0.9857 3200/6993 [============>.................] - ETA: 0s - loss: 0.0796 - accuracy: 0.9866 4096/6993 [================>.............] - ETA: 0s - loss: 0.0710 - accuracy: 0.9871 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0659 - accuracy: 0.9881 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0613 - accuracy: 0.9877 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0623 - accuracy: 0.9878 6993/6993 [==============================] - 1s 79us/sample - loss: 0.0621 - accuracy: 0.9877 - val_loss: 0.6652 - val_accuracy: 0.9323 Epoch 189/199 128/6993 [..............................] - ETA: 1s - loss: 0.0123 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0367 - accuracy: 0.9932 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0504 - accuracy: 0.9905 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0597 - accuracy: 0.9900 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0737 - accuracy: 0.9874 4352/6993 [=================>............] - ETA: 0s - loss: 0.0844 - accuracy: 0.9871 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0909 - accuracy: 0.9867 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0912 - accuracy: 0.9863 6912/6993 [============================>.] - ETA: 0s - loss: 0.0852 - accuracy: 0.9863 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0843 - accuracy: 0.9864 - val_loss: 0.7604 - val_accuracy: 0.9312 Epoch 190/199 128/6993 [..............................] - ETA: 0s - loss: 0.0192 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0337 - accuracy: 0.9893 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0690 - accuracy: 0.9891 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0542 - accuracy: 0.9904 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0631 - accuracy: 0.9892 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0717 - accuracy: 0.9888 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0683 - accuracy: 0.9885 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0741 - accuracy: 0.9880 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0682 - accuracy: 0.9884 - val_loss: 0.7535 - val_accuracy: 0.9257 Epoch 191/199 128/6993 [..............................] - ETA: 0s - loss: 0.0086 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0666 - accuracy: 0.9902 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0881 - accuracy: 0.9859 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0799 - accuracy: 0.9865 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0989 - accuracy: 0.9860 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0976 - accuracy: 0.9866 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0921 - accuracy: 0.9868 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0892 - accuracy: 0.9873 6912/6993 [============================>.] - ETA: 0s - loss: 0.0905 - accuracy: 0.9874 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0895 - accuracy: 0.9876 - val_loss: 0.6966 - val_accuracy: 0.9287 Epoch 192/199 128/6993 [..............................] - ETA: 0s - loss: 0.1559 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0884 - accuracy: 0.9893 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0682 - accuracy: 0.9900 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0596 - accuracy: 0.9903 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0721 - accuracy: 0.9888 4352/6993 [=================>............] - ETA: 0s - loss: 0.0631 - accuracy: 0.9897 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0591 - accuracy: 0.9899 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0701 - accuracy: 0.9889 6784/6993 [============================>.] - ETA: 0s - loss: 0.0702 - accuracy: 0.9881 6993/6993 [==============================] - 1s 78us/sample - loss: 0.0695 - accuracy: 0.9883 - val_loss: 0.7903 - val_accuracy: 0.9277 Epoch 193/199 128/6993 [..............................] - ETA: 0s - loss: 0.0593 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1073 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1694 - accuracy: 0.9851 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1240 - accuracy: 0.9868 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1067 - accuracy: 0.9890 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0888 - accuracy: 0.9895 4352/6993 [=================>............] - ETA: 0s - loss: 0.0822 - accuracy: 0.9892 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0809 - accuracy: 0.9886 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0817 - accuracy: 0.9884 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0804 - accuracy: 0.9876 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0780 - accuracy: 0.9876 - val_loss: 0.7534 - val_accuracy: 0.9257 Epoch 194/199 128/6993 [..............................] - ETA: 0s - loss: 0.0169 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0624 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0580 - accuracy: 0.9908 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0667 - accuracy: 0.9897 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0619 - accuracy: 0.9883 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0610 - accuracy: 0.9887 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0558 - accuracy: 0.9883 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0640 - accuracy: 0.9881 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0601 - accuracy: 0.9878 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0629 - accuracy: 0.9880 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0638 - accuracy: 0.9878 - val_loss: 0.7579 - val_accuracy: 0.9312 Epoch 195/199 128/6993 [..............................] - ETA: 0s - loss: 0.0117 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0637 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0758 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0719 - accuracy: 0.9847 3456/6993 [=============>................] - ETA: 0s - loss: 0.0824 - accuracy: 0.9867 4352/6993 [=================>............] - ETA: 0s - loss: 0.0744 - accuracy: 0.9874 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0739 - accuracy: 0.9876 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0689 - accuracy: 0.9883 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0683 - accuracy: 0.9883 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0703 - accuracy: 0.9880 - val_loss: 0.6781 - val_accuracy: 0.9373 Epoch 196/199 128/6993 [..............................] - ETA: 0s - loss: 0.0035 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0319 - accuracy: 0.9922 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0560 - accuracy: 0.9889 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0595 - accuracy: 0.9910 3328/6993 [=============>................] - ETA: 0s - loss: 0.0563 - accuracy: 0.9901 3968/6993 [================>.............] - ETA: 0s - loss: 0.0538 - accuracy: 0.9904 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0566 - accuracy: 0.9897 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0592 - accuracy: 0.9901 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0607 - accuracy: 0.9894 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0586 - accuracy: 0.9896 - val_loss: 0.7534 - val_accuracy: 0.9257 Epoch 197/199 128/6993 [..............................] - ETA: 0s - loss: 0.0658 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.1153 - accuracy: 0.9891 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0785 - accuracy: 0.9898 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0680 - accuracy: 0.9891 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0805 - accuracy: 0.9871 3328/6993 [=============>................] - ETA: 0s - loss: 0.0820 - accuracy: 0.9859 4096/6993 [================>.............] - ETA: 0s - loss: 0.0798 - accuracy: 0.9858 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1010 - accuracy: 0.9854 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0910 - accuracy: 0.9861 6784/6993 [============================>.] - ETA: 0s - loss: 0.0930 - accuracy: 0.9861 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1028 - accuracy: 0.9863 - val_loss: 0.6752 - val_accuracy: 0.9328 Epoch 198/199 128/6993 [..............................] - ETA: 0s - loss: 0.0034 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0367 - accuracy: 0.9933 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0371 - accuracy: 0.9922 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0373 - accuracy: 0.9918 3328/6993 [=============>................] - ETA: 0s - loss: 0.0414 - accuracy: 0.9907 4224/6993 [=================>............] - ETA: 0s - loss: 0.0406 - accuracy: 0.9891 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0490 - accuracy: 0.9884 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0513 - accuracy: 0.9891 6784/6993 [============================>.] - ETA: 0s - loss: 0.0526 - accuracy: 0.9888 6993/6993 [==============================] - 1s 76us/sample - loss: 0.0516 - accuracy: 0.9890 - val_loss: 0.7247 - val_accuracy: 0.9307 Epoch 199/199 128/6993 [..............................] - ETA: 0s - loss: 0.0480 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0409 - accuracy: 0.9900 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0764 - accuracy: 0.9915 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0780 - accuracy: 0.9918 3200/6993 [============>.................] - ETA: 0s - loss: 0.0757 - accuracy: 0.9916 3968/6993 [================>.............] - ETA: 0s - loss: 0.0717 - accuracy: 0.9907 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0647 - accuracy: 0.9912 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0575 - accuracy: 0.9915 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0565 - accuracy: 0.9911 6993/6993 [==============================] - 1s 80us/sample - loss: 0.0568 - accuracy: 0.9907 - val_loss: 1.0194 - val_accuracy: 0.9221 Evaluating model for iteration 1... 1019/1019 - 0s - loss: 0.8609 - accuracy: 0.9352 Accuracy for iteration 1 0.9352306127548218 Training model for iteration 2... Train on 6993 samples, validate on 1978 samples Epoch 1/199 128/6993 [..............................] - ETA: 21s - loss: 2.3899 - accuracy: 0.0781 896/6993 [==>...........................] - ETA: 3s - loss: 2.1778 - accuracy: 0.1752 1536/6993 [=====>........................] - ETA: 1s - loss: 2.0708 - accuracy: 0.2246 2432/6993 [=========>....................] - ETA: 1s - loss: 1.9641 - accuracy: 0.2685 3200/6993 [============>.................] - ETA: 0s - loss: 1.9044 - accuracy: 0.2931 3840/6993 [===============>..............] - ETA: 0s - loss: 1.8614 - accuracy: 0.3125 4608/6993 [==================>...........] - ETA: 0s - loss: 1.8093 - accuracy: 0.3370 5376/6993 [======================>.......] - ETA: 0s - loss: 1.7744 - accuracy: 0.3508 6272/6993 [=========================>....] - ETA: 0s - loss: 1.7295 - accuracy: 0.3685 6993/6993 [==============================] - 1s 182us/sample - loss: 1.7004 - accuracy: 0.3784 - val_loss: 1.2231 - val_accuracy: 0.5763 Epoch 2/199 128/6993 [..............................] - ETA: 0s - loss: 1.4658 - accuracy: 0.5078 1024/6993 [===>..........................] - ETA: 0s - loss: 1.4357 - accuracy: 0.4951 1792/6993 [======>.......................] - ETA: 0s - loss: 1.3920 - accuracy: 0.5106 2560/6993 [=========>....................] - ETA: 0s - loss: 1.3699 - accuracy: 0.5234 3456/6993 [=============>................] - ETA: 0s - loss: 1.3535 - accuracy: 0.5269 4096/6993 [================>.............] - ETA: 0s - loss: 1.3411 - accuracy: 0.5295 4864/6993 [===================>..........] - ETA: 0s - loss: 1.3327 - accuracy: 0.5335 5760/6993 [=======================>......] - ETA: 0s - loss: 1.3145 - accuracy: 0.5432 6528/6993 [===========================>..] - ETA: 0s - loss: 1.2964 - accuracy: 0.5486 6993/6993 [==============================] - 1s 83us/sample - loss: 1.2798 - accuracy: 0.5558 - val_loss: 0.9591 - val_accuracy: 0.6709 Epoch 3/199 128/6993 [..............................] - ETA: 0s - loss: 0.9570 - accuracy: 0.6562 1024/6993 [===>..........................] - ETA: 0s - loss: 1.0831 - accuracy: 0.6152 1920/6993 [=======>......................] - ETA: 0s - loss: 1.0901 - accuracy: 0.6187 2688/6993 [==========>...................] - ETA: 0s - loss: 1.0621 - accuracy: 0.6310 3328/6993 [=============>................] - ETA: 0s - loss: 1.0721 - accuracy: 0.6334 4096/6993 [================>.............] - ETA: 0s - loss: 1.0674 - accuracy: 0.6382 4992/6993 [====================>.........] - ETA: 0s - loss: 1.0653 - accuracy: 0.6424 5760/6993 [=======================>......] - ETA: 0s - loss: 1.0563 - accuracy: 0.6436 6656/6993 [===========================>..] - ETA: 0s - loss: 1.0562 - accuracy: 0.6420 6993/6993 [==============================] - 1s 81us/sample - loss: 1.0489 - accuracy: 0.6456 - val_loss: 0.8218 - val_accuracy: 0.7189 Epoch 4/199 128/6993 [..............................] - ETA: 0s - loss: 0.9621 - accuracy: 0.6953 768/6993 [==>...........................] - ETA: 0s - loss: 0.9577 - accuracy: 0.6966 1408/6993 [=====>........................] - ETA: 0s - loss: 0.9393 - accuracy: 0.7038 2048/6993 [=======>......................] - ETA: 0s - loss: 0.9261 - accuracy: 0.7026 2816/6993 [===========>..................] - ETA: 0s - loss: 0.9451 - accuracy: 0.6928 3584/6993 [==============>...............] - ETA: 0s - loss: 0.9509 - accuracy: 0.6934 4224/6993 [=================>............] - ETA: 0s - loss: 0.9299 - accuracy: 0.6996 4992/6993 [====================>.........] - ETA: 0s - loss: 0.9120 - accuracy: 0.7039 5760/6993 [=======================>......] - ETA: 0s - loss: 0.9185 - accuracy: 0.6995 6400/6993 [==========================>...] - ETA: 0s - loss: 0.9158 - accuracy: 0.7019 6993/6993 [==============================] - 1s 92us/sample - loss: 0.9135 - accuracy: 0.7000 - val_loss: 0.7526 - val_accuracy: 0.7578 Epoch 5/199 128/6993 [..............................] - ETA: 0s - loss: 0.8857 - accuracy: 0.7656 768/6993 [==>...........................] - ETA: 0s - loss: 0.8217 - accuracy: 0.7331 1536/6993 [=====>........................] - ETA: 0s - loss: 0.8281 - accuracy: 0.7324 2304/6993 [========>.....................] - ETA: 0s - loss: 0.8329 - accuracy: 0.7274 3200/6993 [============>.................] - ETA: 0s - loss: 0.8198 - accuracy: 0.7284 3968/6993 [================>.............] - ETA: 0s - loss: 0.8129 - accuracy: 0.7316 4864/6993 [===================>..........] - ETA: 0s - loss: 0.8194 - accuracy: 0.7296 5504/6993 [======================>.......] - ETA: 0s - loss: 0.8157 - accuracy: 0.7315 6144/6993 [=========================>....] - ETA: 0s - loss: 0.8120 - accuracy: 0.7326 6784/6993 [============================>.] - ETA: 0s - loss: 0.8090 - accuracy: 0.7339 6993/6993 [==============================] - 1s 92us/sample - loss: 0.8089 - accuracy: 0.7342 - val_loss: 0.7058 - val_accuracy: 0.7659 Epoch 6/199 128/6993 [..............................] - ETA: 0s - loss: 0.7494 - accuracy: 0.7969 768/6993 [==>...........................] - ETA: 0s - loss: 0.6532 - accuracy: 0.7917 1408/6993 [=====>........................] - ETA: 0s - loss: 0.6636 - accuracy: 0.7855 2048/6993 [=======>......................] - ETA: 0s - loss: 0.7056 - accuracy: 0.7715 2688/6993 [==========>...................] - ETA: 0s - loss: 0.7198 - accuracy: 0.7653 3328/6993 [=============>................] - ETA: 0s - loss: 0.7242 - accuracy: 0.7683 3968/6993 [================>.............] - ETA: 0s - loss: 0.7176 - accuracy: 0.7702 4480/6993 [==================>...........] - ETA: 0s - loss: 0.7153 - accuracy: 0.7692 4992/6993 [====================>.........] - ETA: 0s - loss: 0.7070 - accuracy: 0.7730 5376/6993 [======================>.......] - ETA: 0s - loss: 0.7101 - accuracy: 0.7734 5888/6993 [========================>.....] - ETA: 0s - loss: 0.7107 - accuracy: 0.7738 6528/6993 [===========================>..] - ETA: 0s - loss: 0.7119 - accuracy: 0.7728 6993/6993 [==============================] - 1s 108us/sample - loss: 0.7157 - accuracy: 0.7721 - val_loss: 0.6266 - val_accuracy: 0.8003 Epoch 7/199 128/6993 [..............................] - ETA: 0s - loss: 0.6576 - accuracy: 0.8281 896/6993 [==>...........................] - ETA: 0s - loss: 0.6539 - accuracy: 0.8013 1664/6993 [======>.......................] - ETA: 0s - loss: 0.6587 - accuracy: 0.7987 2304/6993 [========>.....................] - ETA: 0s - loss: 0.6639 - accuracy: 0.7995 3072/6993 [============>.................] - ETA: 0s - loss: 0.6631 - accuracy: 0.7979 3968/6993 [================>.............] - ETA: 0s - loss: 0.6525 - accuracy: 0.7969 4736/6993 [===================>..........] - ETA: 0s - loss: 0.6419 - accuracy: 0.7981 5632/6993 [=======================>......] - ETA: 0s - loss: 0.6417 - accuracy: 0.7967 6400/6993 [==========================>...] - ETA: 0s - loss: 0.6396 - accuracy: 0.7970 6993/6993 [==============================] - 1s 87us/sample - loss: 0.6365 - accuracy: 0.7978 - val_loss: 0.5756 - val_accuracy: 0.8089 Epoch 8/199 128/6993 [..............................] - ETA: 0s - loss: 0.5597 - accuracy: 0.8359 896/6993 [==>...........................] - ETA: 0s - loss: 0.5948 - accuracy: 0.8170 1664/6993 [======>.......................] - ETA: 0s - loss: 0.5825 - accuracy: 0.8167 2560/6993 [=========>....................] - ETA: 0s - loss: 0.5943 - accuracy: 0.8145 3072/6993 [============>.................] - ETA: 0s - loss: 0.5870 - accuracy: 0.8174 3840/6993 [===============>..............] - ETA: 0s - loss: 0.5819 - accuracy: 0.8208 4608/6993 [==================>...........] - ETA: 0s - loss: 0.5771 - accuracy: 0.8192 5504/6993 [======================>.......] - ETA: 0s - loss: 0.5715 - accuracy: 0.8218 6272/6993 [=========================>....] - ETA: 0s - loss: 0.5764 - accuracy: 0.8203 6993/6993 [==============================] - 1s 85us/sample - loss: 0.5747 - accuracy: 0.8208 - val_loss: 0.5693 - val_accuracy: 0.8210 Epoch 9/199 128/6993 [..............................] - ETA: 0s - loss: 0.6025 - accuracy: 0.8125 896/6993 [==>...........................] - ETA: 0s - loss: 0.5581 - accuracy: 0.8147 1536/6993 [=====>........................] - ETA: 0s - loss: 0.5368 - accuracy: 0.8262 2304/6993 [========>.....................] - ETA: 0s - loss: 0.5371 - accuracy: 0.8299 3200/6993 [============>.................] - ETA: 0s - loss: 0.5298 - accuracy: 0.8341 3968/6993 [================>.............] - ETA: 0s - loss: 0.5264 - accuracy: 0.8342 4864/6993 [===================>..........] - ETA: 0s - loss: 0.5375 - accuracy: 0.8341 5632/6993 [=======================>......] - ETA: 0s - loss: 0.5362 - accuracy: 0.8375 6528/6993 [===========================>..] - ETA: 0s - loss: 0.5348 - accuracy: 0.8384 6993/6993 [==============================] - 1s 81us/sample - loss: 0.5340 - accuracy: 0.8388 - val_loss: 0.5514 - val_accuracy: 0.8195 Epoch 10/199 128/6993 [..............................] - ETA: 0s - loss: 0.4935 - accuracy: 0.8516 896/6993 [==>...........................] - ETA: 0s - loss: 0.4542 - accuracy: 0.8616 1408/6993 [=====>........................] - ETA: 0s - loss: 0.4463 - accuracy: 0.8587 2048/6993 [=======>......................] - ETA: 0s - loss: 0.4428 - accuracy: 0.8608 2816/6993 [===========>..................] - ETA: 0s - loss: 0.4646 - accuracy: 0.8544 3712/6993 [==============>...............] - ETA: 0s - loss: 0.4801 - accuracy: 0.8532 4480/6993 [==================>...........] - ETA: 0s - loss: 0.4867 - accuracy: 0.8507 5248/6993 [=====================>........] - ETA: 0s - loss: 0.4880 - accuracy: 0.8491 5760/6993 [=======================>......] - ETA: 0s - loss: 0.4863 - accuracy: 0.8500 6400/6993 [==========================>...] - ETA: 0s - loss: 0.4924 - accuracy: 0.8497 6993/6993 [==============================] - 1s 92us/sample - loss: 0.4965 - accuracy: 0.8480 - val_loss: 0.5274 - val_accuracy: 0.8387 Epoch 11/199 128/6993 [..............................] - ETA: 0s - loss: 0.3626 - accuracy: 0.8828 896/6993 [==>...........................] - ETA: 0s - loss: 0.4467 - accuracy: 0.8694 1664/6993 [======>.......................] - ETA: 0s - loss: 0.4500 - accuracy: 0.8594 2560/6993 [=========>....................] - ETA: 0s - loss: 0.4298 - accuracy: 0.8660 3328/6993 [=============>................] - ETA: 0s - loss: 0.4336 - accuracy: 0.8612 4224/6993 [=================>............] - ETA: 0s - loss: 0.4364 - accuracy: 0.8610 4992/6993 [====================>.........] - ETA: 0s - loss: 0.4345 - accuracy: 0.8594 5632/6993 [=======================>......] - ETA: 0s - loss: 0.4402 - accuracy: 0.8580 6528/6993 [===========================>..] - ETA: 0s - loss: 0.4440 - accuracy: 0.8571 6993/6993 [==============================] - 1s 81us/sample - loss: 0.4448 - accuracy: 0.8563 - val_loss: 0.4708 - val_accuracy: 0.8534 Epoch 12/199 128/6993 [..............................] - ETA: 0s - loss: 0.3566 - accuracy: 0.9062 1024/6993 [===>..........................] - ETA: 0s - loss: 0.3778 - accuracy: 0.8828 1792/6993 [======>.......................] - ETA: 0s - loss: 0.4032 - accuracy: 0.8761 2688/6993 [==========>...................] - ETA: 0s - loss: 0.3936 - accuracy: 0.8824 3456/6993 [=============>................] - ETA: 0s - loss: 0.3937 - accuracy: 0.8805 4352/6993 [=================>............] - ETA: 0s - loss: 0.3948 - accuracy: 0.8814 5120/6993 [====================>.........] - ETA: 0s - loss: 0.3951 - accuracy: 0.8803 6016/6993 [========================>.....] - ETA: 0s - loss: 0.3967 - accuracy: 0.8792 6784/6993 [============================>.] - ETA: 0s - loss: 0.4022 - accuracy: 0.8769 6993/6993 [==============================] - 1s 81us/sample - loss: 0.4033 - accuracy: 0.8764 - val_loss: 0.4307 - val_accuracy: 0.8696 Epoch 13/199 128/6993 [..............................] - ETA: 0s - loss: 0.3309 - accuracy: 0.8984 768/6993 [==>...........................] - ETA: 0s - loss: 0.3204 - accuracy: 0.8945 1536/6993 [=====>........................] - ETA: 0s - loss: 0.3396 - accuracy: 0.8965 2304/6993 [========>.....................] - ETA: 0s - loss: 0.3530 - accuracy: 0.8893 2944/6993 [===========>..................] - ETA: 0s - loss: 0.3590 - accuracy: 0.8865 3712/6993 [==============>...............] - ETA: 0s - loss: 0.3593 - accuracy: 0.8871 4480/6993 [==================>...........] - ETA: 0s - loss: 0.3752 - accuracy: 0.8835 5120/6993 [====================>.........] - ETA: 0s - loss: 0.3729 - accuracy: 0.8842 5888/6993 [========================>.....] - ETA: 0s - loss: 0.3776 - accuracy: 0.8835 6784/6993 [============================>.] - ETA: 0s - loss: 0.3817 - accuracy: 0.8827 6993/6993 [==============================] - 1s 89us/sample - loss: 0.3814 - accuracy: 0.8836 - val_loss: 0.4004 - val_accuracy: 0.8716 Epoch 14/199 128/6993 [..............................] - ETA: 0s - loss: 0.3102 - accuracy: 0.8984 896/6993 [==>...........................] - ETA: 0s - loss: 0.3180 - accuracy: 0.9129 1664/6993 [======>.......................] - ETA: 0s - loss: 0.3206 - accuracy: 0.9069 2560/6993 [=========>....................] - ETA: 0s - loss: 0.3383 - accuracy: 0.8992 3200/6993 [============>.................] - ETA: 0s - loss: 0.3572 - accuracy: 0.8956 3968/6993 [================>.............] - ETA: 0s - loss: 0.3583 - accuracy: 0.8914 4480/6993 [==================>...........] - ETA: 0s - loss: 0.3490 - accuracy: 0.8946 5248/6993 [=====================>........] - ETA: 0s - loss: 0.3416 - accuracy: 0.8967 5888/6993 [========================>.....] - ETA: 0s - loss: 0.3482 - accuracy: 0.8961 6528/6993 [===========================>..] - ETA: 0s - loss: 0.3476 - accuracy: 0.8958 6993/6993 [==============================] - 1s 92us/sample - loss: 0.3521 - accuracy: 0.8936 - val_loss: 0.4202 - val_accuracy: 0.8792 Epoch 15/199 128/6993 [..............................] - ETA: 0s - loss: 0.2597 - accuracy: 0.8984 896/6993 [==>...........................] - ETA: 0s - loss: 0.3144 - accuracy: 0.8951 1792/6993 [======>.......................] - ETA: 0s - loss: 0.3081 - accuracy: 0.8973 2560/6993 [=========>....................] - ETA: 0s - loss: 0.3143 - accuracy: 0.8988 3456/6993 [=============>................] - ETA: 0s - loss: 0.3245 - accuracy: 0.8973 4224/6993 [=================>............] - ETA: 0s - loss: 0.3327 - accuracy: 0.8965 4992/6993 [====================>.........] - ETA: 0s - loss: 0.3415 - accuracy: 0.8936 5760/6993 [=======================>......] - ETA: 0s - loss: 0.3330 - accuracy: 0.8979 6528/6993 [===========================>..] - ETA: 0s - loss: 0.3338 - accuracy: 0.8980 6993/6993 [==============================] - 1s 83us/sample - loss: 0.3455 - accuracy: 0.8963 - val_loss: 0.4103 - val_accuracy: 0.8761 Epoch 16/199 128/6993 [..............................] - ETA: 0s - loss: 0.2675 - accuracy: 0.9141 896/6993 [==>...........................] - ETA: 0s - loss: 0.3250 - accuracy: 0.8951 1792/6993 [======>.......................] - ETA: 0s - loss: 0.3131 - accuracy: 0.9029 2432/6993 [=========>....................] - ETA: 0s - loss: 0.3172 - accuracy: 0.9009 3200/6993 [============>.................] - ETA: 0s - loss: 0.3027 - accuracy: 0.9038 3968/6993 [================>.............] - ETA: 0s - loss: 0.3189 - accuracy: 0.9012 4864/6993 [===================>..........] - ETA: 0s - loss: 0.3111 - accuracy: 0.9032 5632/6993 [=======================>......] - ETA: 0s - loss: 0.3138 - accuracy: 0.9016 6528/6993 [===========================>..] - ETA: 0s - loss: 0.3089 - accuracy: 0.9032 6993/6993 [==============================] - 1s 83us/sample - loss: 0.3039 - accuracy: 0.9046 - val_loss: 0.4465 - val_accuracy: 0.8711 Epoch 17/199 128/6993 [..............................] - ETA: 0s - loss: 0.2501 - accuracy: 0.9297 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2367 - accuracy: 0.9258 1664/6993 [======>.......................] - ETA: 0s - loss: 0.2385 - accuracy: 0.9243 2432/6993 [=========>....................] - ETA: 0s - loss: 0.2748 - accuracy: 0.9165 3200/6993 [============>.................] - ETA: 0s - loss: 0.2640 - accuracy: 0.9178 4096/6993 [================>.............] - ETA: 0s - loss: 0.2682 - accuracy: 0.9177 4864/6993 [===================>..........] - ETA: 0s - loss: 0.2717 - accuracy: 0.9178 5760/6993 [=======================>......] - ETA: 0s - loss: 0.2730 - accuracy: 0.9170 6528/6993 [===========================>..] - ETA: 0s - loss: 0.2797 - accuracy: 0.9138 6993/6993 [==============================] - 1s 83us/sample - loss: 0.2828 - accuracy: 0.9122 - val_loss: 0.4185 - val_accuracy: 0.8756 Epoch 18/199 128/6993 [..............................] - ETA: 0s - loss: 0.3389 - accuracy: 0.8906 896/6993 [==>...........................] - ETA: 0s - loss: 0.2706 - accuracy: 0.9219 1664/6993 [======>.......................] - ETA: 0s - loss: 0.2547 - accuracy: 0.9273 2432/6993 [=========>....................] - ETA: 0s - loss: 0.2581 - accuracy: 0.9239 3328/6993 [=============>................] - ETA: 0s - loss: 0.2601 - accuracy: 0.9234 4096/6993 [================>.............] - ETA: 0s - loss: 0.2509 - accuracy: 0.9265 4864/6993 [===================>..........] - ETA: 0s - loss: 0.2477 - accuracy: 0.9264 5760/6993 [=======================>......] - ETA: 0s - loss: 0.2571 - accuracy: 0.9234 6528/6993 [===========================>..] - ETA: 0s - loss: 0.2602 - accuracy: 0.9225 6993/6993 [==============================] - 1s 83us/sample - loss: 0.2593 - accuracy: 0.9228 - val_loss: 0.4021 - val_accuracy: 0.8908 Epoch 19/199 128/6993 [..............................] - ETA: 1s - loss: 0.2018 - accuracy: 0.9531 896/6993 [==>...........................] - ETA: 0s - loss: 0.2460 - accuracy: 0.9241 1792/6993 [======>.......................] - ETA: 0s - loss: 0.2446 - accuracy: 0.9247 2560/6993 [=========>....................] - ETA: 0s - loss: 0.2416 - accuracy: 0.9270 3456/6993 [=============>................] - ETA: 0s - loss: 0.2496 - accuracy: 0.9248 4224/6993 [=================>............] - ETA: 0s - loss: 0.2495 - accuracy: 0.9254 5120/6993 [====================>.........] - ETA: 0s - loss: 0.2531 - accuracy: 0.9240 5888/6993 [========================>.....] - ETA: 0s - loss: 0.2552 - accuracy: 0.9232 6784/6993 [============================>.] - ETA: 0s - loss: 0.2569 - accuracy: 0.9231 6993/6993 [==============================] - 1s 83us/sample - loss: 0.2552 - accuracy: 0.9239 - val_loss: 0.3692 - val_accuracy: 0.8923 Epoch 20/199 128/6993 [..............................] - ETA: 0s - loss: 0.2928 - accuracy: 0.9219 896/6993 [==>...........................] - ETA: 0s - loss: 0.2487 - accuracy: 0.9286 1664/6993 [======>.......................] - ETA: 0s - loss: 0.2208 - accuracy: 0.9327 2560/6993 [=========>....................] - ETA: 0s - loss: 0.2171 - accuracy: 0.9336 3328/6993 [=============>................] - ETA: 0s - loss: 0.2257 - accuracy: 0.9309 4224/6993 [=================>............] - ETA: 0s - loss: 0.2303 - accuracy: 0.9306 4992/6993 [====================>.........] - ETA: 0s - loss: 0.2239 - accuracy: 0.9319 5888/6993 [========================>.....] - ETA: 0s - loss: 0.2300 - accuracy: 0.9317 6528/6993 [===========================>..] - ETA: 0s - loss: 0.2330 - accuracy: 0.9305 6993/6993 [==============================] - 1s 80us/sample - loss: 0.2327 - accuracy: 0.9305 - val_loss: 0.4038 - val_accuracy: 0.8888 Epoch 21/199 128/6993 [..............................] - ETA: 0s - loss: 0.2267 - accuracy: 0.9297 896/6993 [==>...........................] - ETA: 0s - loss: 0.2019 - accuracy: 0.9408 1792/6993 [======>.......................] - ETA: 0s - loss: 0.2212 - accuracy: 0.9347 2688/6993 [==========>...................] - ETA: 0s - loss: 0.2195 - accuracy: 0.9304 3456/6993 [=============>................] - ETA: 0s - loss: 0.2060 - accuracy: 0.9332 4352/6993 [=================>............] - ETA: 0s - loss: 0.2097 - accuracy: 0.9327 5120/6993 [====================>.........] - ETA: 0s - loss: 0.2092 - accuracy: 0.9324 5888/6993 [========================>.....] - ETA: 0s - loss: 0.2153 - accuracy: 0.9319 6784/6993 [============================>.] - ETA: 0s - loss: 0.2138 - accuracy: 0.9318 6993/6993 [==============================] - 1s 81us/sample - loss: 0.2127 - accuracy: 0.9316 - val_loss: 0.4138 - val_accuracy: 0.8857 Epoch 22/199 128/6993 [..............................] - ETA: 0s - loss: 0.2720 - accuracy: 0.9375 896/6993 [==>...........................] - ETA: 0s - loss: 0.2239 - accuracy: 0.9431 1536/6993 [=====>........................] - ETA: 0s - loss: 0.2049 - accuracy: 0.9414 2304/6993 [========>.....................] - ETA: 0s - loss: 0.2086 - accuracy: 0.9384 2944/6993 [===========>..................] - ETA: 0s - loss: 0.2056 - accuracy: 0.9402 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1968 - accuracy: 0.9421 4480/6993 [==================>...........] - ETA: 0s - loss: 0.2057 - accuracy: 0.9422 4992/6993 [====================>.........] - ETA: 0s - loss: 0.2085 - accuracy: 0.9393 5888/6993 [========================>.....] - ETA: 0s - loss: 0.2044 - accuracy: 0.9411 6656/6993 [===========================>..] - ETA: 0s - loss: 0.2078 - accuracy: 0.9402 6993/6993 [==============================] - 1s 87us/sample - loss: 0.2066 - accuracy: 0.9407 - val_loss: 0.3834 - val_accuracy: 0.8959 Epoch 23/199 128/6993 [..............................] - ETA: 0s - loss: 0.1395 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.1497 - accuracy: 0.9554 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1538 - accuracy: 0.9561 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1842 - accuracy: 0.9465 3328/6993 [=============>................] - ETA: 0s - loss: 0.1969 - accuracy: 0.9426 3968/6993 [================>.............] - ETA: 0s - loss: 0.1991 - accuracy: 0.9423 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1970 - accuracy: 0.9431 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1971 - accuracy: 0.9420 5760/6993 [=======================>......] - ETA: 0s - loss: 0.2094 - accuracy: 0.9406 6400/6993 [==========================>...] - ETA: 0s - loss: 0.2089 - accuracy: 0.9403 6993/6993 [==============================] - 1s 94us/sample - loss: 0.2064 - accuracy: 0.9409 - val_loss: 0.4358 - val_accuracy: 0.8903 Epoch 24/199 128/6993 [..............................] - ETA: 0s - loss: 0.2519 - accuracy: 0.9219 896/6993 [==>...........................] - ETA: 0s - loss: 0.1756 - accuracy: 0.9408 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1869 - accuracy: 0.9436 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1967 - accuracy: 0.9430 3456/6993 [=============>................] - ETA: 0s - loss: 0.1849 - accuracy: 0.9459 4352/6993 [=================>............] - ETA: 0s - loss: 0.1862 - accuracy: 0.9451 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1852 - accuracy: 0.9455 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1825 - accuracy: 0.9471 6784/6993 [============================>.] - ETA: 0s - loss: 0.1822 - accuracy: 0.9463 6993/6993 [==============================] - 1s 81us/sample - loss: 0.1848 - accuracy: 0.9454 - val_loss: 0.4315 - val_accuracy: 0.8943 Epoch 25/199 128/6993 [..............................] - ETA: 0s - loss: 0.2152 - accuracy: 0.9297 896/6993 [==>...........................] - ETA: 0s - loss: 0.2265 - accuracy: 0.9353 1664/6993 [======>.......................] - ETA: 0s - loss: 0.2019 - accuracy: 0.9411 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1875 - accuracy: 0.9497 3072/6993 [============>.................] - ETA: 0s - loss: 0.1850 - accuracy: 0.9508 3968/6993 [================>.............] - ETA: 0s - loss: 0.1770 - accuracy: 0.9509 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1797 - accuracy: 0.9483 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1807 - accuracy: 0.9492 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1875 - accuracy: 0.9478 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1869 - accuracy: 0.9484 - val_loss: 0.4260 - val_accuracy: 0.8888 Epoch 26/199 128/6993 [..............................] - ETA: 0s - loss: 0.1067 - accuracy: 0.9609 768/6993 [==>...........................] - ETA: 0s - loss: 0.1359 - accuracy: 0.9544 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1491 - accuracy: 0.9517 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1479 - accuracy: 0.9526 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1527 - accuracy: 0.9542 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1603 - accuracy: 0.9494 4352/6993 [=================>............] - ETA: 0s - loss: 0.1571 - accuracy: 0.9506 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1547 - accuracy: 0.9517 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1630 - accuracy: 0.9506 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1638 - accuracy: 0.9505 6993/6993 [==============================] - 1s 86us/sample - loss: 0.1658 - accuracy: 0.9502 - val_loss: 0.4348 - val_accuracy: 0.8943 Epoch 27/199 128/6993 [..............................] - ETA: 0s - loss: 0.1800 - accuracy: 0.9531 896/6993 [==>...........................] - ETA: 0s - loss: 0.1824 - accuracy: 0.9654 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1660 - accuracy: 0.9626 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1557 - accuracy: 0.9617 3456/6993 [=============>................] - ETA: 0s - loss: 0.1559 - accuracy: 0.9589 4352/6993 [=================>............] - ETA: 0s - loss: 0.1556 - accuracy: 0.9582 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1567 - accuracy: 0.9568 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1563 - accuracy: 0.9560 6784/6993 [============================>.] - ETA: 0s - loss: 0.1584 - accuracy: 0.9558 6993/6993 [==============================] - 1s 82us/sample - loss: 0.1596 - accuracy: 0.9561 - val_loss: 0.4379 - val_accuracy: 0.8979 Epoch 28/199 128/6993 [..............................] - ETA: 0s - loss: 0.1923 - accuracy: 0.9531 768/6993 [==>...........................] - ETA: 0s - loss: 0.1539 - accuracy: 0.9544 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1496 - accuracy: 0.9602 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1399 - accuracy: 0.9639 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1576 - accuracy: 0.9621 3328/6993 [=============>................] - ETA: 0s - loss: 0.1704 - accuracy: 0.9582 3968/6993 [================>.............] - ETA: 0s - loss: 0.1712 - accuracy: 0.9587 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1703 - accuracy: 0.9564 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1729 - accuracy: 0.9559 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1748 - accuracy: 0.9553 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1751 - accuracy: 0.9549 6993/6993 [==============================] - 1s 89us/sample - loss: 0.1748 - accuracy: 0.9547 - val_loss: 0.3725 - val_accuracy: 0.9070 Epoch 29/199 128/6993 [..............................] - ETA: 0s - loss: 0.1080 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.1138 - accuracy: 0.9688 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1132 - accuracy: 0.9675 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1120 - accuracy: 0.9659 3200/6993 [============>.................] - ETA: 0s - loss: 0.1248 - accuracy: 0.9622 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1328 - accuracy: 0.9607 4352/6993 [=================>............] - ETA: 0s - loss: 0.1365 - accuracy: 0.9600 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1316 - accuracy: 0.9617 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1314 - accuracy: 0.9620 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1389 - accuracy: 0.9608 6993/6993 [==============================] - 1s 90us/sample - loss: 0.1377 - accuracy: 0.9608 - val_loss: 0.4223 - val_accuracy: 0.8959 Epoch 30/199 128/6993 [..............................] - ETA: 0s - loss: 0.1652 - accuracy: 0.9375 896/6993 [==>...........................] - ETA: 0s - loss: 0.1336 - accuracy: 0.9609 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1416 - accuracy: 0.9645 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1414 - accuracy: 0.9660 3328/6993 [=============>................] - ETA: 0s - loss: 0.1625 - accuracy: 0.9585 4224/6993 [=================>............] - ETA: 0s - loss: 0.1516 - accuracy: 0.9600 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1479 - accuracy: 0.9597 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1588 - accuracy: 0.9562 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1604 - accuracy: 0.9555 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1611 - accuracy: 0.9552 - val_loss: 0.3907 - val_accuracy: 0.9070 Epoch 31/199 128/6993 [..............................] - ETA: 0s - loss: 0.2139 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.1609 - accuracy: 0.9531 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1696 - accuracy: 0.9519 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1539 - accuracy: 0.9566 3072/6993 [============>.................] - ETA: 0s - loss: 0.1466 - accuracy: 0.9580 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1433 - accuracy: 0.9591 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1494 - accuracy: 0.9577 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1507 - accuracy: 0.9576 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1489 - accuracy: 0.9577 6993/6993 [==============================] - 1s 87us/sample - loss: 0.1516 - accuracy: 0.9568 - val_loss: 0.3869 - val_accuracy: 0.9105 Epoch 32/199 128/6993 [..............................] - ETA: 0s - loss: 0.2115 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.1817 - accuracy: 0.9596 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1702 - accuracy: 0.9597 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1615 - accuracy: 0.9593 3200/6993 [============>.................] - ETA: 0s - loss: 0.1611 - accuracy: 0.9569 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1566 - accuracy: 0.9586 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1518 - accuracy: 0.9600 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1576 - accuracy: 0.9590 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1565 - accuracy: 0.9585 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1581 - accuracy: 0.9583 6993/6993 [==============================] - 1s 94us/sample - loss: 0.1549 - accuracy: 0.9585 - val_loss: 0.4267 - val_accuracy: 0.9060 Epoch 33/199 128/6993 [..............................] - ETA: 0s - loss: 0.0609 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1260 - accuracy: 0.9674 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1419 - accuracy: 0.9609 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1308 - accuracy: 0.9648 3072/6993 [============>.................] - ETA: 0s - loss: 0.1188 - accuracy: 0.9684 3968/6993 [================>.............] - ETA: 0s - loss: 0.1324 - accuracy: 0.9655 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1379 - accuracy: 0.9616 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1398 - accuracy: 0.9624 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1428 - accuracy: 0.9603 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1416 - accuracy: 0.9605 - val_loss: 0.4015 - val_accuracy: 0.9075 Epoch 34/199 128/6993 [..............................] - ETA: 0s - loss: 0.1840 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.1142 - accuracy: 0.9721 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0972 - accuracy: 0.9766 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1204 - accuracy: 0.9684 3328/6993 [=============>................] - ETA: 0s - loss: 0.1235 - accuracy: 0.9675 4224/6993 [=================>............] - ETA: 0s - loss: 0.1268 - accuracy: 0.9664 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1250 - accuracy: 0.9673 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1280 - accuracy: 0.9664 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1397 - accuracy: 0.9640 6912/6993 [============================>.] - ETA: 0s - loss: 0.1416 - accuracy: 0.9634 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1427 - accuracy: 0.9632 - val_loss: 0.4123 - val_accuracy: 0.9075 Epoch 35/199 128/6993 [..............................] - ETA: 0s - loss: 0.2088 - accuracy: 0.9453 896/6993 [==>...........................] - ETA: 0s - loss: 0.1502 - accuracy: 0.9643 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1460 - accuracy: 0.9603 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1324 - accuracy: 0.9628 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1335 - accuracy: 0.9627 3456/6993 [=============>................] - ETA: 0s - loss: 0.1398 - accuracy: 0.9630 4096/6993 [================>.............] - ETA: 0s - loss: 0.1326 - accuracy: 0.9634 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1284 - accuracy: 0.9645 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1276 - accuracy: 0.9641 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1269 - accuracy: 0.9638 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1264 - accuracy: 0.9639 6993/6993 [==============================] - 1s 94us/sample - loss: 0.1302 - accuracy: 0.9631 - val_loss: 0.3883 - val_accuracy: 0.9146 Epoch 36/199 128/6993 [..............................] - ETA: 0s - loss: 0.0718 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0733 - accuracy: 0.9740 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1017 - accuracy: 0.9645 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1116 - accuracy: 0.9648 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1059 - accuracy: 0.9673 3328/6993 [=============>................] - ETA: 0s - loss: 0.1086 - accuracy: 0.9681 3968/6993 [================>.............] - ETA: 0s - loss: 0.1199 - accuracy: 0.9670 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1267 - accuracy: 0.9668 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1269 - accuracy: 0.9676 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1236 - accuracy: 0.9678 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1207 - accuracy: 0.9684 6912/6993 [============================>.] - ETA: 0s - loss: 0.1190 - accuracy: 0.9688 6993/6993 [==============================] - 1s 95us/sample - loss: 0.1187 - accuracy: 0.9687 - val_loss: 0.4438 - val_accuracy: 0.9085 Epoch 37/199 128/6993 [..............................] - ETA: 0s - loss: 0.0292 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0772 - accuracy: 0.9719 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0822 - accuracy: 0.9757 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1029 - accuracy: 0.9706 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1160 - accuracy: 0.9669 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1154 - accuracy: 0.9655 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1190 - accuracy: 0.9659 3328/6993 [=============>................] - ETA: 0s - loss: 0.1128 - accuracy: 0.9675 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1174 - accuracy: 0.9677 4096/6993 [================>.............] - ETA: 0s - loss: 0.1232 - accuracy: 0.9673 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1262 - accuracy: 0.9667 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1305 - accuracy: 0.9655 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1252 - accuracy: 0.9661 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1264 - accuracy: 0.9656 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1261 - accuracy: 0.9655 6912/6993 [============================>.] - ETA: 0s - loss: 0.1297 - accuracy: 0.9648 6993/6993 [==============================] - 1s 138us/sample - loss: 0.1288 - accuracy: 0.9651 - val_loss: 0.4024 - val_accuracy: 0.9141 Epoch 38/199 128/6993 [..............................] - ETA: 0s - loss: 0.0894 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.1124 - accuracy: 0.9719 1152/6993 [===>..........................] - ETA: 0s - loss: 0.1058 - accuracy: 0.9714 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1008 - accuracy: 0.9736 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1170 - accuracy: 0.9701 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1041 - accuracy: 0.9728 3200/6993 [============>.................] - ETA: 0s - loss: 0.1036 - accuracy: 0.9722 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1013 - accuracy: 0.9714 4224/6993 [=================>............] - ETA: 0s - loss: 0.1100 - accuracy: 0.9697 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1099 - accuracy: 0.9698 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1146 - accuracy: 0.9691 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1116 - accuracy: 0.9693 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1105 - accuracy: 0.9701 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1096 - accuracy: 0.9702 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1150 - accuracy: 0.9691 6993/6993 [==============================] - 1s 135us/sample - loss: 0.1117 - accuracy: 0.9700 - val_loss: 0.4533 - val_accuracy: 0.9090 Epoch 39/199 128/6993 [..............................] - ETA: 0s - loss: 0.1094 - accuracy: 0.9766 512/6993 [=>............................] - ETA: 0s - loss: 0.1003 - accuracy: 0.9688 1152/6993 [===>..........................] - ETA: 0s - loss: 0.1258 - accuracy: 0.9644 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1327 - accuracy: 0.9627 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1298 - accuracy: 0.9642 3200/6993 [============>.................] - ETA: 0s - loss: 0.1356 - accuracy: 0.9641 3968/6993 [================>.............] - ETA: 0s - loss: 0.1246 - accuracy: 0.9655 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1232 - accuracy: 0.9650 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1228 - accuracy: 0.9650 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1210 - accuracy: 0.9660 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1181 - accuracy: 0.9660 6912/6993 [============================>.] - ETA: 0s - loss: 0.1170 - accuracy: 0.9664 6993/6993 [==============================] - 1s 112us/sample - loss: 0.1191 - accuracy: 0.9660 - val_loss: 0.5183 - val_accuracy: 0.8898 Epoch 40/199 128/6993 [..............................] - ETA: 0s - loss: 0.1226 - accuracy: 0.9375 512/6993 [=>............................] - ETA: 0s - loss: 0.0844 - accuracy: 0.9590 896/6993 [==>...........................] - ETA: 0s - loss: 0.0788 - accuracy: 0.9643 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0815 - accuracy: 0.9688 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0928 - accuracy: 0.9693 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1027 - accuracy: 0.9659 3072/6993 [============>.................] - ETA: 0s - loss: 0.1162 - accuracy: 0.9658 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1175 - accuracy: 0.9657 4224/6993 [=================>............] - ETA: 0s - loss: 0.1217 - accuracy: 0.9650 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1228 - accuracy: 0.9649 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1181 - accuracy: 0.9652 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1196 - accuracy: 0.9643 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1229 - accuracy: 0.9642 6993/6993 [==============================] - 1s 112us/sample - loss: 0.1222 - accuracy: 0.9642 - val_loss: 0.4111 - val_accuracy: 0.9115 Epoch 41/199 128/6993 [..............................] - ETA: 1s - loss: 0.0303 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.0491 - accuracy: 0.9781 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0807 - accuracy: 0.9766 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0860 - accuracy: 0.9729 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0858 - accuracy: 0.9715 3200/6993 [============>.................] - ETA: 0s - loss: 0.0862 - accuracy: 0.9709 3968/6993 [================>.............] - ETA: 0s - loss: 0.0967 - accuracy: 0.9695 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0960 - accuracy: 0.9703 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1005 - accuracy: 0.9697 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1050 - accuracy: 0.9689 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1065 - accuracy: 0.9688 6993/6993 [==============================] - 1s 101us/sample - loss: 0.1128 - accuracy: 0.9685 - val_loss: 0.4507 - val_accuracy: 0.9004 Epoch 42/199 128/6993 [..............................] - ETA: 0s - loss: 0.2695 - accuracy: 0.9375 768/6993 [==>...........................] - ETA: 0s - loss: 0.1237 - accuracy: 0.9622 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1295 - accuracy: 0.9652 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1220 - accuracy: 0.9655 3072/6993 [============>.................] - ETA: 0s - loss: 0.1209 - accuracy: 0.9661 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1146 - accuracy: 0.9688 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1095 - accuracy: 0.9707 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1100 - accuracy: 0.9703 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1125 - accuracy: 0.9698 6993/6993 [==============================] - 1s 90us/sample - loss: 0.1138 - accuracy: 0.9697 - val_loss: 0.4565 - val_accuracy: 0.9141 Epoch 43/199 128/6993 [..............................] - ETA: 0s - loss: 0.0599 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0762 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0797 - accuracy: 0.9801 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0897 - accuracy: 0.9770 3072/6993 [============>.................] - ETA: 0s - loss: 0.0973 - accuracy: 0.9749 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0972 - accuracy: 0.9737 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1021 - accuracy: 0.9721 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0999 - accuracy: 0.9727 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1055 - accuracy: 0.9712 6993/6993 [==============================] - 1s 84us/sample - loss: 0.1079 - accuracy: 0.9705 - val_loss: 0.4253 - val_accuracy: 0.9156 Epoch 44/199 128/6993 [..............................] - ETA: 0s - loss: 0.0216 - accuracy: 1.0000 640/6993 [=>............................] - ETA: 0s - loss: 0.0769 - accuracy: 0.9766 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1163 - accuracy: 0.9719 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1097 - accuracy: 0.9703 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1041 - accuracy: 0.9719 3200/6993 [============>.................] - ETA: 0s - loss: 0.0946 - accuracy: 0.9744 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0903 - accuracy: 0.9749 4352/6993 [=================>............] - ETA: 0s - loss: 0.1043 - accuracy: 0.9731 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1119 - accuracy: 0.9721 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1103 - accuracy: 0.9714 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1108 - accuracy: 0.9711 6993/6993 [==============================] - 1s 93us/sample - loss: 0.1083 - accuracy: 0.9713 - val_loss: 0.4196 - val_accuracy: 0.9135 Epoch 45/199 128/6993 [..............................] - ETA: 0s - loss: 0.0614 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1529 - accuracy: 0.9688 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1146 - accuracy: 0.9704 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1032 - accuracy: 0.9717 3456/6993 [=============>................] - ETA: 0s - loss: 0.1018 - accuracy: 0.9690 4224/6993 [=================>............] - ETA: 0s - loss: 0.0957 - accuracy: 0.9699 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0936 - accuracy: 0.9696 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0988 - accuracy: 0.9700 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0994 - accuracy: 0.9705 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0972 - accuracy: 0.9703 - val_loss: 0.4077 - val_accuracy: 0.9186 Epoch 46/199 128/6993 [..............................] - ETA: 0s - loss: 0.0717 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1003 - accuracy: 0.9777 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1050 - accuracy: 0.9721 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1122 - accuracy: 0.9703 3456/6993 [=============>................] - ETA: 0s - loss: 0.1135 - accuracy: 0.9693 4096/6993 [================>.............] - ETA: 0s - loss: 0.1117 - accuracy: 0.9697 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1152 - accuracy: 0.9696 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1113 - accuracy: 0.9710 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1060 - accuracy: 0.9724 6993/6993 [==============================] - 1s 84us/sample - loss: 0.1082 - accuracy: 0.9723 - val_loss: 0.4301 - val_accuracy: 0.9130 Epoch 47/199 128/6993 [..............................] - ETA: 0s - loss: 0.0403 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1055 - accuracy: 0.9701 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0860 - accuracy: 0.9751 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0878 - accuracy: 0.9756 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0957 - accuracy: 0.9728 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0997 - accuracy: 0.9724 4224/6993 [=================>............] - ETA: 0s - loss: 0.0991 - accuracy: 0.9732 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1012 - accuracy: 0.9731 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0961 - accuracy: 0.9740 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0979 - accuracy: 0.9727 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1048 - accuracy: 0.9722 6993/6993 [==============================] - 1s 92us/sample - loss: 0.1064 - accuracy: 0.9714 - val_loss: 0.3950 - val_accuracy: 0.9191 Epoch 48/199 128/6993 [..............................] - ETA: 0s - loss: 0.0882 - accuracy: 0.9609 768/6993 [==>...........................] - ETA: 0s - loss: 0.1186 - accuracy: 0.9674 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1042 - accuracy: 0.9709 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1105 - accuracy: 0.9724 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1099 - accuracy: 0.9712 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1021 - accuracy: 0.9734 3200/6993 [============>.................] - ETA: 0s - loss: 0.1002 - accuracy: 0.9734 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0958 - accuracy: 0.9743 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1020 - accuracy: 0.9740 4224/6993 [=================>............] - ETA: 0s - loss: 0.0975 - accuracy: 0.9754 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0975 - accuracy: 0.9755 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0968 - accuracy: 0.9760 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0959 - accuracy: 0.9760 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0974 - accuracy: 0.9757 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0947 - accuracy: 0.9766 6993/6993 [==============================] - 1s 128us/sample - loss: 0.0958 - accuracy: 0.9761 - val_loss: 0.4412 - val_accuracy: 0.9151 Epoch 49/199 128/6993 [..............................] - ETA: 0s - loss: 0.1688 - accuracy: 0.9609 768/6993 [==>...........................] - ETA: 0s - loss: 0.0915 - accuracy: 0.9831 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0834 - accuracy: 0.9828 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0887 - accuracy: 0.9805 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0960 - accuracy: 0.9766 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0931 - accuracy: 0.9777 3072/6993 [============>.................] - ETA: 0s - loss: 0.1090 - accuracy: 0.9759 3328/6993 [=============>................] - ETA: 0s - loss: 0.1067 - accuracy: 0.9766 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0993 - accuracy: 0.9779 4096/6993 [================>.............] - ETA: 0s - loss: 0.1035 - accuracy: 0.9768 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1044 - accuracy: 0.9766 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1066 - accuracy: 0.9756 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1071 - accuracy: 0.9753 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1038 - accuracy: 0.9757 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1005 - accuracy: 0.9761 6912/6993 [============================>.] - ETA: 0s - loss: 0.1021 - accuracy: 0.9758 6993/6993 [==============================] - 1s 137us/sample - loss: 0.1020 - accuracy: 0.9758 - val_loss: 0.4805 - val_accuracy: 0.9141 Epoch 50/199 128/6993 [..............................] - ETA: 0s - loss: 0.1623 - accuracy: 0.9531 640/6993 [=>............................] - ETA: 0s - loss: 0.1110 - accuracy: 0.9656 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0926 - accuracy: 0.9748 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0935 - accuracy: 0.9736 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0909 - accuracy: 0.9752 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0888 - accuracy: 0.9754 3072/6993 [============>.................] - ETA: 0s - loss: 0.0897 - accuracy: 0.9753 3456/6993 [=============>................] - ETA: 0s - loss: 0.0919 - accuracy: 0.9734 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1050 - accuracy: 0.9727 4224/6993 [=================>............] - ETA: 0s - loss: 0.1129 - accuracy: 0.9721 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1093 - accuracy: 0.9727 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1055 - accuracy: 0.9730 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1048 - accuracy: 0.9737 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1033 - accuracy: 0.9732 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1035 - accuracy: 0.9731 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1007 - accuracy: 0.9739 6993/6993 [==============================] - 1s 148us/sample - loss: 0.1043 - accuracy: 0.9735 - val_loss: 0.4467 - val_accuracy: 0.9151 Epoch 51/199 128/6993 [..............................] - ETA: 0s - loss: 0.0771 - accuracy: 0.9844 512/6993 [=>............................] - ETA: 0s - loss: 0.0386 - accuracy: 0.9902 896/6993 [==>...........................] - ETA: 0s - loss: 0.0641 - accuracy: 0.9821 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0862 - accuracy: 0.9781 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0922 - accuracy: 0.9784 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0890 - accuracy: 0.9780 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0912 - accuracy: 0.9778 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0910 - accuracy: 0.9776 3200/6993 [============>.................] - ETA: 0s - loss: 0.0873 - accuracy: 0.9781 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0939 - accuracy: 0.9766 4224/6993 [=================>............] - ETA: 0s - loss: 0.0932 - accuracy: 0.9768 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0940 - accuracy: 0.9763 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0916 - accuracy: 0.9766 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0923 - accuracy: 0.9766 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0910 - accuracy: 0.9764 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0899 - accuracy: 0.9766 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0908 - accuracy: 0.9763 6993/6993 [==============================] - 1s 152us/sample - loss: 0.0902 - accuracy: 0.9764 - val_loss: 0.4506 - val_accuracy: 0.9196 Epoch 52/199 128/6993 [..............................] - ETA: 0s - loss: 0.0221 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0446 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0588 - accuracy: 0.9837 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0668 - accuracy: 0.9807 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0739 - accuracy: 0.9790 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0859 - accuracy: 0.9769 3456/6993 [=============>................] - ETA: 0s - loss: 0.0985 - accuracy: 0.9742 3968/6993 [================>.............] - ETA: 0s - loss: 0.0931 - accuracy: 0.9751 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1014 - accuracy: 0.9737 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1030 - accuracy: 0.9734 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1017 - accuracy: 0.9741 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0986 - accuracy: 0.9746 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0990 - accuracy: 0.9746 6993/6993 [==============================] - 1s 120us/sample - loss: 0.1008 - accuracy: 0.9737 - val_loss: 0.4874 - val_accuracy: 0.9034 Epoch 53/199 128/6993 [..............................] - ETA: 0s - loss: 0.0770 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.0825 - accuracy: 0.9734 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0911 - accuracy: 0.9696 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0845 - accuracy: 0.9749 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0827 - accuracy: 0.9749 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0797 - accuracy: 0.9769 3456/6993 [=============>................] - ETA: 0s - loss: 0.0903 - accuracy: 0.9766 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0888 - accuracy: 0.9766 4352/6993 [=================>............] - ETA: 0s - loss: 0.0841 - accuracy: 0.9775 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0842 - accuracy: 0.9770 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0831 - accuracy: 0.9775 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0836 - accuracy: 0.9766 6784/6993 [============================>.] - ETA: 0s - loss: 0.0843 - accuracy: 0.9766 6993/6993 [==============================] - 1s 111us/sample - loss: 0.0847 - accuracy: 0.9760 - val_loss: 0.4267 - val_accuracy: 0.9221 Epoch 54/199 128/6993 [..............................] - ETA: 0s - loss: 0.0883 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.0636 - accuracy: 0.9766 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0558 - accuracy: 0.9818 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0734 - accuracy: 0.9790 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0788 - accuracy: 0.9779 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0845 - accuracy: 0.9766 3072/6993 [============>.................] - ETA: 0s - loss: 0.0903 - accuracy: 0.9753 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0871 - accuracy: 0.9752 4096/6993 [================>.............] - ETA: 0s - loss: 0.0896 - accuracy: 0.9753 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1010 - accuracy: 0.9741 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1042 - accuracy: 0.9733 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0988 - accuracy: 0.9745 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0991 - accuracy: 0.9745 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0999 - accuracy: 0.9735 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1096 - accuracy: 0.9721 6993/6993 [==============================] - 1s 136us/sample - loss: 0.1076 - accuracy: 0.9723 - val_loss: 0.4486 - val_accuracy: 0.9247 Epoch 55/199 128/6993 [..............................] - ETA: 0s - loss: 0.0514 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.0919 - accuracy: 0.9703 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0911 - accuracy: 0.9696 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0865 - accuracy: 0.9742 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0887 - accuracy: 0.9744 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0798 - accuracy: 0.9773 3072/6993 [============>.................] - ETA: 0s - loss: 0.0841 - accuracy: 0.9762 3456/6993 [=============>................] - ETA: 0s - loss: 0.0944 - accuracy: 0.9742 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0907 - accuracy: 0.9740 4352/6993 [=================>............] - ETA: 0s - loss: 0.0878 - accuracy: 0.9750 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0941 - accuracy: 0.9751 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0925 - accuracy: 0.9751 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0943 - accuracy: 0.9752 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0908 - accuracy: 0.9766 6993/6993 [==============================] - 1s 124us/sample - loss: 0.0905 - accuracy: 0.9765 - val_loss: 0.4370 - val_accuracy: 0.9221 Epoch 56/199 128/6993 [..............................] - ETA: 0s - loss: 0.0818 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0867 - accuracy: 0.9766 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0718 - accuracy: 0.9801 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0750 - accuracy: 0.9790 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0734 - accuracy: 0.9793 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0727 - accuracy: 0.9796 3456/6993 [=============>................] - ETA: 0s - loss: 0.0738 - accuracy: 0.9795 3968/6993 [================>.............] - ETA: 0s - loss: 0.0725 - accuracy: 0.9796 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0765 - accuracy: 0.9781 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0761 - accuracy: 0.9782 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0782 - accuracy: 0.9769 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0852 - accuracy: 0.9761 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0834 - accuracy: 0.9761 6993/6993 [==============================] - 1s 117us/sample - loss: 0.0832 - accuracy: 0.9764 - val_loss: 0.4156 - val_accuracy: 0.9262 Epoch 57/199 128/6993 [..............................] - ETA: 0s - loss: 0.1160 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.1148 - accuracy: 0.9672 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0914 - accuracy: 0.9748 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0829 - accuracy: 0.9766 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0918 - accuracy: 0.9761 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0905 - accuracy: 0.9777 3200/6993 [============>.................] - ETA: 0s - loss: 0.0871 - accuracy: 0.9772 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0850 - accuracy: 0.9771 4096/6993 [================>.............] - ETA: 0s - loss: 0.0844 - accuracy: 0.9773 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0830 - accuracy: 0.9770 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0812 - accuracy: 0.9779 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0821 - accuracy: 0.9773 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0846 - accuracy: 0.9767 6784/6993 [============================>.] - ETA: 0s - loss: 0.0876 - accuracy: 0.9767 6993/6993 [==============================] - 1s 124us/sample - loss: 0.0879 - accuracy: 0.9765 - val_loss: 0.4568 - val_accuracy: 0.9151 Epoch 58/199 128/6993 [..............................] - ETA: 0s - loss: 0.0565 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.0527 - accuracy: 0.9875 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0676 - accuracy: 0.9826 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0639 - accuracy: 0.9831 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0742 - accuracy: 0.9807 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0807 - accuracy: 0.9793 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0857 - accuracy: 0.9781 3072/6993 [============>.................] - ETA: 0s - loss: 0.0853 - accuracy: 0.9782 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0904 - accuracy: 0.9768 3968/6993 [================>.............] - ETA: 0s - loss: 0.0924 - accuracy: 0.9771 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0886 - accuracy: 0.9783 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0870 - accuracy: 0.9782 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0871 - accuracy: 0.9782 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0866 - accuracy: 0.9778 6912/6993 [============================>.] - ETA: 0s - loss: 0.0898 - accuracy: 0.9774 6993/6993 [==============================] - 1s 131us/sample - loss: 0.0894 - accuracy: 0.9777 - val_loss: 0.4447 - val_accuracy: 0.9186 Epoch 59/199 128/6993 [..............................] - ETA: 0s - loss: 0.0857 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.0934 - accuracy: 0.9766 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0751 - accuracy: 0.9826 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0763 - accuracy: 0.9790 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0738 - accuracy: 0.9793 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0729 - accuracy: 0.9788 3200/6993 [============>.................] - ETA: 0s - loss: 0.0740 - accuracy: 0.9791 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0741 - accuracy: 0.9793 4352/6993 [=================>............] - ETA: 0s - loss: 0.0751 - accuracy: 0.9791 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0813 - accuracy: 0.9779 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0811 - accuracy: 0.9781 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0829 - accuracy: 0.9780 6993/6993 [==============================] - 1s 105us/sample - loss: 0.0817 - accuracy: 0.9781 - val_loss: 0.4953 - val_accuracy: 0.9176 Epoch 60/199 128/6993 [..............................] - ETA: 0s - loss: 0.0466 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0996 - accuracy: 0.9818 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1034 - accuracy: 0.9787 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1019 - accuracy: 0.9800 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0973 - accuracy: 0.9799 3328/6993 [=============>................] - ETA: 0s - loss: 0.0950 - accuracy: 0.9790 3968/6993 [================>.............] - ETA: 0s - loss: 0.1049 - accuracy: 0.9761 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0997 - accuracy: 0.9768 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0943 - accuracy: 0.9773 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0944 - accuracy: 0.9774 6784/6993 [============================>.] - ETA: 0s - loss: 0.0921 - accuracy: 0.9776 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0930 - accuracy: 0.9771 - val_loss: 0.4594 - val_accuracy: 0.9196 Epoch 61/199 128/6993 [..............................] - ETA: 0s - loss: 0.0922 - accuracy: 0.9609 640/6993 [=>............................] - ETA: 0s - loss: 0.1254 - accuracy: 0.9734 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1099 - accuracy: 0.9711 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1022 - accuracy: 0.9721 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0924 - accuracy: 0.9749 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1021 - accuracy: 0.9759 3456/6993 [=============>................] - ETA: 0s - loss: 0.0951 - accuracy: 0.9771 3968/6993 [================>.............] - ETA: 0s - loss: 0.0862 - accuracy: 0.9796 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0809 - accuracy: 0.9800 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0816 - accuracy: 0.9795 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0835 - accuracy: 0.9787 6912/6993 [============================>.] - ETA: 0s - loss: 0.0851 - accuracy: 0.9783 6993/6993 [==============================] - 1s 97us/sample - loss: 0.0846 - accuracy: 0.9784 - val_loss: 0.5103 - val_accuracy: 0.9146 Epoch 62/199 128/6993 [..............................] - ETA: 0s - loss: 0.1339 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0938 - accuracy: 0.9766 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0818 - accuracy: 0.9779 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0691 - accuracy: 0.9807 3072/6993 [============>.................] - ETA: 0s - loss: 0.0640 - accuracy: 0.9824 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0705 - accuracy: 0.9826 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0681 - accuracy: 0.9830 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0719 - accuracy: 0.9818 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0782 - accuracy: 0.9811 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0779 - accuracy: 0.9808 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0770 - accuracy: 0.9810 - val_loss: 0.4749 - val_accuracy: 0.9211 Epoch 63/199 128/6993 [..............................] - ETA: 0s - loss: 0.0905 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0978 - accuracy: 0.9799 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0993 - accuracy: 0.9785 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0857 - accuracy: 0.9789 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1004 - accuracy: 0.9798 3456/6993 [=============>................] - ETA: 0s - loss: 0.0943 - accuracy: 0.9789 4096/6993 [================>.............] - ETA: 0s - loss: 0.0903 - accuracy: 0.9792 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0946 - accuracy: 0.9774 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0912 - accuracy: 0.9781 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1004 - accuracy: 0.9769 6784/6993 [============================>.] - ETA: 0s - loss: 0.0976 - accuracy: 0.9770 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0959 - accuracy: 0.9773 - val_loss: 0.5689 - val_accuracy: 0.9034 Epoch 64/199 128/6993 [..............................] - ETA: 0s - loss: 0.1220 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0628 - accuracy: 0.9844 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0677 - accuracy: 0.9805 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0761 - accuracy: 0.9776 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0741 - accuracy: 0.9781 3328/6993 [=============>................] - ETA: 0s - loss: 0.0749 - accuracy: 0.9790 3968/6993 [================>.............] - ETA: 0s - loss: 0.0795 - accuracy: 0.9778 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0795 - accuracy: 0.9789 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0766 - accuracy: 0.9797 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0754 - accuracy: 0.9798 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0794 - accuracy: 0.9789 6912/6993 [============================>.] - ETA: 0s - loss: 0.0789 - accuracy: 0.9786 6993/6993 [==============================] - 1s 106us/sample - loss: 0.0790 - accuracy: 0.9785 - val_loss: 0.5273 - val_accuracy: 0.9221 Epoch 65/199 128/6993 [..............................] - ETA: 0s - loss: 0.0522 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0760 - accuracy: 0.9766 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0842 - accuracy: 0.9778 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0807 - accuracy: 0.9774 3072/6993 [============>.................] - ETA: 0s - loss: 0.0892 - accuracy: 0.9766 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1007 - accuracy: 0.9766 4352/6993 [=================>............] - ETA: 0s - loss: 0.1010 - accuracy: 0.9756 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0937 - accuracy: 0.9772 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0894 - accuracy: 0.9779 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0938 - accuracy: 0.9767 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0921 - accuracy: 0.9768 - val_loss: 0.5013 - val_accuracy: 0.9211 Epoch 66/199 128/6993 [..............................] - ETA: 0s - loss: 0.0190 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0449 - accuracy: 0.9909 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0582 - accuracy: 0.9870 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0653 - accuracy: 0.9848 3072/6993 [============>.................] - ETA: 0s - loss: 0.0822 - accuracy: 0.9814 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0795 - accuracy: 0.9817 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0827 - accuracy: 0.9807 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0875 - accuracy: 0.9797 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0904 - accuracy: 0.9793 6912/6993 [============================>.] - ETA: 0s - loss: 0.0898 - accuracy: 0.9787 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0890 - accuracy: 0.9788 - val_loss: 0.4390 - val_accuracy: 0.9262 Epoch 67/199 128/6993 [..............................] - ETA: 0s - loss: 0.0669 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1348 - accuracy: 0.9721 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1143 - accuracy: 0.9766 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1047 - accuracy: 0.9792 3072/6993 [============>.................] - ETA: 0s - loss: 0.0908 - accuracy: 0.9801 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0854 - accuracy: 0.9807 4352/6993 [=================>............] - ETA: 0s - loss: 0.0834 - accuracy: 0.9814 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0803 - accuracy: 0.9817 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0897 - accuracy: 0.9808 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0871 - accuracy: 0.9811 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0843 - accuracy: 0.9813 - val_loss: 0.5062 - val_accuracy: 0.9191 Epoch 68/199 128/6993 [..............................] - ETA: 0s - loss: 0.0400 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0873 - accuracy: 0.9818 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0806 - accuracy: 0.9838 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0759 - accuracy: 0.9835 3200/6993 [============>.................] - ETA: 0s - loss: 0.0871 - accuracy: 0.9806 3968/6993 [================>.............] - ETA: 0s - loss: 0.0866 - accuracy: 0.9806 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0850 - accuracy: 0.9821 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0869 - accuracy: 0.9822 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0844 - accuracy: 0.9822 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0823 - accuracy: 0.9819 6784/6993 [============================>.] - ETA: 0s - loss: 0.0807 - accuracy: 0.9814 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0788 - accuracy: 0.9818 - val_loss: 0.4941 - val_accuracy: 0.9247 Epoch 69/199 128/6993 [..............................] - ETA: 0s - loss: 0.1623 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.0913 - accuracy: 0.9844 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0658 - accuracy: 0.9878 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0600 - accuracy: 0.9874 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0632 - accuracy: 0.9862 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0591 - accuracy: 0.9862 3328/6993 [=============>................] - ETA: 0s - loss: 0.0645 - accuracy: 0.9832 3968/6993 [================>.............] - ETA: 0s - loss: 0.0653 - accuracy: 0.9826 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0733 - accuracy: 0.9818 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0728 - accuracy: 0.9814 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0683 - accuracy: 0.9823 6993/6993 [==============================] - 1s 104us/sample - loss: 0.0653 - accuracy: 0.9830 - val_loss: 0.4644 - val_accuracy: 0.9237 Epoch 70/199 128/6993 [..............................] - ETA: 0s - loss: 0.0308 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0704 - accuracy: 0.9810 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0817 - accuracy: 0.9782 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0772 - accuracy: 0.9781 3328/6993 [=============>................] - ETA: 0s - loss: 0.0941 - accuracy: 0.9775 4224/6993 [=================>............] - ETA: 0s - loss: 0.0878 - accuracy: 0.9777 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0845 - accuracy: 0.9784 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0799 - accuracy: 0.9798 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0861 - accuracy: 0.9791 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0841 - accuracy: 0.9796 - val_loss: 0.4269 - val_accuracy: 0.9262 Epoch 71/199 128/6993 [..............................] - ETA: 0s - loss: 0.0642 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.1071 - accuracy: 0.9792 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0918 - accuracy: 0.9797 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0734 - accuracy: 0.9833 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0738 - accuracy: 0.9820 3200/6993 [============>.................] - ETA: 0s - loss: 0.0707 - accuracy: 0.9831 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0707 - accuracy: 0.9836 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0643 - accuracy: 0.9848 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0646 - accuracy: 0.9849 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0738 - accuracy: 0.9831 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0741 - accuracy: 0.9827 - val_loss: 0.4434 - val_accuracy: 0.9247 Epoch 72/199 128/6993 [..............................] - ETA: 0s - loss: 0.0267 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0823 - accuracy: 0.9743 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1075 - accuracy: 0.9754 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1006 - accuracy: 0.9762 3328/6993 [=============>................] - ETA: 0s - loss: 0.0864 - accuracy: 0.9793 3968/6993 [================>.............] - ETA: 0s - loss: 0.0835 - accuracy: 0.9791 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0849 - accuracy: 0.9794 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0876 - accuracy: 0.9798 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0862 - accuracy: 0.9806 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0847 - accuracy: 0.9802 6912/6993 [============================>.] - ETA: 0s - loss: 0.0807 - accuracy: 0.9808 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0800 - accuracy: 0.9808 - val_loss: 0.4169 - val_accuracy: 0.9242 Epoch 73/199 128/6993 [..............................] - ETA: 0s - loss: 0.0128 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0262 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0423 - accuracy: 0.9851 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0408 - accuracy: 0.9855 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0483 - accuracy: 0.9852 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0650 - accuracy: 0.9820 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0650 - accuracy: 0.9820 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0632 - accuracy: 0.9822 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0690 - accuracy: 0.9810 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0764 - accuracy: 0.9806 6784/6993 [============================>.] - ETA: 0s - loss: 0.0770 - accuracy: 0.9805 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0770 - accuracy: 0.9804 - val_loss: 0.4391 - val_accuracy: 0.9312 Epoch 74/199 128/6993 [..............................] - ETA: 0s - loss: 0.0871 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.1205 - accuracy: 0.9688 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0979 - accuracy: 0.9737 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0846 - accuracy: 0.9781 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0822 - accuracy: 0.9793 3200/6993 [============>.................] - ETA: 0s - loss: 0.0831 - accuracy: 0.9794 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0775 - accuracy: 0.9803 4352/6993 [=================>............] - ETA: 0s - loss: 0.0771 - accuracy: 0.9802 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0778 - accuracy: 0.9802 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0768 - accuracy: 0.9795 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0789 - accuracy: 0.9796 6993/6993 [==============================] - 1s 102us/sample - loss: 0.0784 - accuracy: 0.9800 - val_loss: 0.4605 - val_accuracy: 0.9191 Epoch 75/199 128/6993 [..............................] - ETA: 0s - loss: 0.0901 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0832 - accuracy: 0.9834 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9855 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0705 - accuracy: 0.9819 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0687 - accuracy: 0.9813 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0733 - accuracy: 0.9807 4224/6993 [=================>............] - ETA: 0s - loss: 0.0702 - accuracy: 0.9818 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0799 - accuracy: 0.9809 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0850 - accuracy: 0.9783 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0866 - accuracy: 0.9783 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0883 - accuracy: 0.9775 - val_loss: 0.4523 - val_accuracy: 0.9166 Epoch 76/199 128/6993 [..............................] - ETA: 0s - loss: 0.0297 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0458 - accuracy: 0.9877 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0719 - accuracy: 0.9838 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0777 - accuracy: 0.9816 3456/6993 [=============>................] - ETA: 0s - loss: 0.0740 - accuracy: 0.9829 4224/6993 [=================>............] - ETA: 0s - loss: 0.0712 - accuracy: 0.9825 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0754 - accuracy: 0.9818 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0703 - accuracy: 0.9825 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0723 - accuracy: 0.9820 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0704 - accuracy: 0.9823 - val_loss: 0.4716 - val_accuracy: 0.9287 Epoch 77/199 128/6993 [..............................] - ETA: 0s - loss: 0.0844 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0924 - accuracy: 0.9788 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0692 - accuracy: 0.9802 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0706 - accuracy: 0.9823 3072/6993 [============>.................] - ETA: 0s - loss: 0.0800 - accuracy: 0.9811 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0930 - accuracy: 0.9798 4352/6993 [=================>............] - ETA: 0s - loss: 0.0953 - accuracy: 0.9786 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0886 - accuracy: 0.9796 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0906 - accuracy: 0.9792 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0890 - accuracy: 0.9797 6784/6993 [============================>.] - ETA: 0s - loss: 0.0910 - accuracy: 0.9791 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0900 - accuracy: 0.9793 - val_loss: 0.4992 - val_accuracy: 0.9161 Epoch 78/199 128/6993 [..............................] - ETA: 0s - loss: 0.0436 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0497 - accuracy: 0.9855 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0476 - accuracy: 0.9856 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0540 - accuracy: 0.9828 3328/6993 [=============>................] - ETA: 0s - loss: 0.0606 - accuracy: 0.9811 4096/6993 [================>.............] - ETA: 0s - loss: 0.0691 - accuracy: 0.9800 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0725 - accuracy: 0.9800 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0758 - accuracy: 0.9797 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0749 - accuracy: 0.9790 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0745 - accuracy: 0.9788 - val_loss: 0.4772 - val_accuracy: 0.9237 Epoch 79/199 128/6993 [..............................] - ETA: 0s - loss: 0.0462 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0649 - accuracy: 0.9855 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0558 - accuracy: 0.9862 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0520 - accuracy: 0.9863 3328/6993 [=============>................] - ETA: 0s - loss: 0.0517 - accuracy: 0.9880 4224/6993 [=================>............] - ETA: 0s - loss: 0.0683 - accuracy: 0.9851 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0686 - accuracy: 0.9840 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0694 - accuracy: 0.9826 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0740 - accuracy: 0.9809 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0726 - accuracy: 0.9816 - val_loss: 0.4969 - val_accuracy: 0.9176 Epoch 80/199 128/6993 [..............................] - ETA: 0s - loss: 0.1896 - accuracy: 0.9609 768/6993 [==>...........................] - ETA: 0s - loss: 0.1309 - accuracy: 0.9766 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1038 - accuracy: 0.9760 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1093 - accuracy: 0.9778 3328/6993 [=============>................] - ETA: 0s - loss: 0.0984 - accuracy: 0.9781 4096/6993 [================>.............] - ETA: 0s - loss: 0.0956 - accuracy: 0.9783 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0931 - accuracy: 0.9784 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0837 - accuracy: 0.9809 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0804 - accuracy: 0.9813 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0789 - accuracy: 0.9814 - val_loss: 0.3880 - val_accuracy: 0.9307 Epoch 81/199 128/6993 [..............................] - ETA: 0s - loss: 0.0245 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0999 - accuracy: 0.9777 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0661 - accuracy: 0.9832 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0629 - accuracy: 0.9844 3200/6993 [============>.................] - ETA: 0s - loss: 0.0683 - accuracy: 0.9841 3968/6993 [================>.............] - ETA: 0s - loss: 0.0672 - accuracy: 0.9844 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0712 - accuracy: 0.9840 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0733 - accuracy: 0.9830 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0851 - accuracy: 0.9817 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0872 - accuracy: 0.9818 - val_loss: 0.3886 - val_accuracy: 0.9292 Epoch 82/199 128/6993 [..............................] - ETA: 0s - loss: 0.0192 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0750 - accuracy: 0.9877 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0744 - accuracy: 0.9826 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0753 - accuracy: 0.9819 3200/6993 [============>.................] - ETA: 0s - loss: 0.0757 - accuracy: 0.9812 4096/6993 [================>.............] - ETA: 0s - loss: 0.0747 - accuracy: 0.9812 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0734 - accuracy: 0.9813 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0800 - accuracy: 0.9809 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0766 - accuracy: 0.9821 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0736 - accuracy: 0.9824 - val_loss: 0.5031 - val_accuracy: 0.9232 Epoch 83/199 128/6993 [..............................] - ETA: 0s - loss: 0.1397 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1095 - accuracy: 0.9799 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0927 - accuracy: 0.9796 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0831 - accuracy: 0.9824 3328/6993 [=============>................] - ETA: 0s - loss: 0.0845 - accuracy: 0.9799 4224/6993 [=================>............] - ETA: 0s - loss: 0.0739 - accuracy: 0.9820 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0762 - accuracy: 0.9808 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0825 - accuracy: 0.9812 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0903 - accuracy: 0.9793 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0875 - accuracy: 0.9800 - val_loss: 0.4539 - val_accuracy: 0.9206 Epoch 84/199 128/6993 [..............................] - ETA: 0s - loss: 0.0721 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0784 - accuracy: 0.9788 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0751 - accuracy: 0.9785 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0617 - accuracy: 0.9802 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0631 - accuracy: 0.9815 3456/6993 [=============>................] - ETA: 0s - loss: 0.0683 - accuracy: 0.9818 4096/6993 [================>.............] - ETA: 0s - loss: 0.0670 - accuracy: 0.9834 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0714 - accuracy: 0.9833 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0827 - accuracy: 0.9830 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0797 - accuracy: 0.9837 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0796 - accuracy: 0.9840 - val_loss: 0.4743 - val_accuracy: 0.9221 Epoch 85/199 128/6993 [..............................] - ETA: 0s - loss: 0.0586 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0896 - accuracy: 0.9805 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0589 - accuracy: 0.9855 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0562 - accuracy: 0.9851 3456/6993 [=============>................] - ETA: 0s - loss: 0.0674 - accuracy: 0.9832 4352/6993 [=================>............] - ETA: 0s - loss: 0.0751 - accuracy: 0.9821 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0787 - accuracy: 0.9818 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0738 - accuracy: 0.9825 6784/6993 [============================>.] - ETA: 0s - loss: 0.0737 - accuracy: 0.9826 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0719 - accuracy: 0.9830 - val_loss: 0.5093 - val_accuracy: 0.9257 Epoch 86/199 128/6993 [..............................] - ETA: 0s - loss: 0.1523 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0717 - accuracy: 0.9896 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0756 - accuracy: 0.9850 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0631 - accuracy: 0.9867 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0585 - accuracy: 0.9872 3328/6993 [=============>................] - ETA: 0s - loss: 0.0623 - accuracy: 0.9865 3968/6993 [================>.............] - ETA: 0s - loss: 0.0592 - accuracy: 0.9861 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0588 - accuracy: 0.9855 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0654 - accuracy: 0.9846 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0627 - accuracy: 0.9847 6784/6993 [============================>.] - ETA: 0s - loss: 0.0616 - accuracy: 0.9847 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0636 - accuracy: 0.9843 - val_loss: 0.7360 - val_accuracy: 0.8964 Epoch 87/199 128/6993 [..............................] - ETA: 0s - loss: 0.2555 - accuracy: 0.9531 896/6993 [==>...........................] - ETA: 0s - loss: 0.0970 - accuracy: 0.9788 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0754 - accuracy: 0.9827 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0620 - accuracy: 0.9844 3456/6993 [=============>................] - ETA: 0s - loss: 0.0643 - accuracy: 0.9841 4096/6993 [================>.............] - ETA: 0s - loss: 0.0650 - accuracy: 0.9846 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0731 - accuracy: 0.9837 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0808 - accuracy: 0.9807 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0819 - accuracy: 0.9809 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0860 - accuracy: 0.9801 - val_loss: 0.4732 - val_accuracy: 0.9237 Epoch 88/199 128/6993 [..............................] - ETA: 0s - loss: 0.0846 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0514 - accuracy: 0.9855 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0490 - accuracy: 0.9838 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0485 - accuracy: 0.9864 3328/6993 [=============>................] - ETA: 0s - loss: 0.0514 - accuracy: 0.9853 4096/6993 [================>.............] - ETA: 0s - loss: 0.0513 - accuracy: 0.9854 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0558 - accuracy: 0.9850 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0627 - accuracy: 0.9842 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0700 - accuracy: 0.9829 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0709 - accuracy: 0.9828 - val_loss: 0.4903 - val_accuracy: 0.9166 Epoch 89/199 128/6993 [..............................] - ETA: 0s - loss: 0.0329 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0590 - accuracy: 0.9833 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0632 - accuracy: 0.9816 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0708 - accuracy: 0.9805 3456/6993 [=============>................] - ETA: 0s - loss: 0.0756 - accuracy: 0.9800 4224/6993 [=================>............] - ETA: 0s - loss: 0.0700 - accuracy: 0.9815 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0693 - accuracy: 0.9822 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0655 - accuracy: 0.9832 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0690 - accuracy: 0.9833 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0690 - accuracy: 0.9828 - val_loss: 0.4894 - val_accuracy: 0.9317 Epoch 90/199 128/6993 [..............................] - ETA: 0s - loss: 0.0277 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.0979 - accuracy: 0.9781 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0861 - accuracy: 0.9785 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1021 - accuracy: 0.9779 3072/6993 [============>.................] - ETA: 0s - loss: 0.0967 - accuracy: 0.9785 3968/6993 [================>.............] - ETA: 0s - loss: 0.0865 - accuracy: 0.9808 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0806 - accuracy: 0.9821 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0742 - accuracy: 0.9828 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0748 - accuracy: 0.9836 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0741 - accuracy: 0.9834 - val_loss: 0.5658 - val_accuracy: 0.9201 Epoch 91/199 128/6993 [..............................] - ETA: 0s - loss: 0.0207 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0540 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0601 - accuracy: 0.9866 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0578 - accuracy: 0.9863 3328/6993 [=============>................] - ETA: 0s - loss: 0.0546 - accuracy: 0.9877 4224/6993 [=================>............] - ETA: 0s - loss: 0.0636 - accuracy: 0.9853 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0631 - accuracy: 0.9858 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0624 - accuracy: 0.9852 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0611 - accuracy: 0.9857 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0634 - accuracy: 0.9853 - val_loss: 0.5663 - val_accuracy: 0.9242 Epoch 92/199 128/6993 [..............................] - ETA: 0s - loss: 0.0759 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0277 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0538 - accuracy: 0.9905 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0508 - accuracy: 0.9892 3456/6993 [=============>................] - ETA: 0s - loss: 0.0609 - accuracy: 0.9878 4096/6993 [================>.............] - ETA: 0s - loss: 0.0726 - accuracy: 0.9873 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0752 - accuracy: 0.9854 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0733 - accuracy: 0.9852 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0748 - accuracy: 0.9847 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0725 - accuracy: 0.9850 - val_loss: 0.4911 - val_accuracy: 0.9257 Epoch 93/199 128/6993 [..............................] - ETA: 0s - loss: 0.0387 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0393 - accuracy: 0.9870 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0630 - accuracy: 0.9837 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0585 - accuracy: 0.9848 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0620 - accuracy: 0.9837 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0597 - accuracy: 0.9841 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0674 - accuracy: 0.9824 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0650 - accuracy: 0.9823 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0685 - accuracy: 0.9820 6912/6993 [============================>.] - ETA: 0s - loss: 0.0639 - accuracy: 0.9826 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0643 - accuracy: 0.9824 - val_loss: 0.5636 - val_accuracy: 0.9247 Epoch 94/199 128/6993 [..............................] - ETA: 0s - loss: 0.0064 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1017 - accuracy: 0.9766 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0845 - accuracy: 0.9788 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0848 - accuracy: 0.9809 3456/6993 [=============>................] - ETA: 0s - loss: 0.0769 - accuracy: 0.9821 4224/6993 [=================>............] - ETA: 0s - loss: 0.0845 - accuracy: 0.9834 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0830 - accuracy: 0.9842 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0836 - accuracy: 0.9840 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0788 - accuracy: 0.9839 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0762 - accuracy: 0.9841 - val_loss: 0.5474 - val_accuracy: 0.9206 Epoch 95/199 128/6993 [..............................] - ETA: 0s - loss: 0.0458 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0824 - accuracy: 0.9805 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0928 - accuracy: 0.9779 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0895 - accuracy: 0.9789 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0805 - accuracy: 0.9801 3456/6993 [=============>................] - ETA: 0s - loss: 0.0865 - accuracy: 0.9777 4096/6993 [================>.............] - ETA: 0s - loss: 0.0801 - accuracy: 0.9790 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0751 - accuracy: 0.9802 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0769 - accuracy: 0.9803 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0723 - accuracy: 0.9817 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0698 - accuracy: 0.9816 - val_loss: 0.5979 - val_accuracy: 0.9272 Epoch 96/199 128/6993 [..............................] - ETA: 0s - loss: 0.0093 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0970 - accuracy: 0.9805 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0970 - accuracy: 0.9816 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0910 - accuracy: 0.9820 3328/6993 [=============>................] - ETA: 0s - loss: 0.0792 - accuracy: 0.9829 4224/6993 [=================>............] - ETA: 0s - loss: 0.0825 - accuracy: 0.9839 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0772 - accuracy: 0.9840 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0720 - accuracy: 0.9845 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0780 - accuracy: 0.9836 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0759 - accuracy: 0.9838 - val_loss: 0.4401 - val_accuracy: 0.9307 Epoch 97/199 128/6993 [..............................] - ETA: 0s - loss: 0.1083 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1723 - accuracy: 0.9824 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1137 - accuracy: 0.9872 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1294 - accuracy: 0.9844 3456/6993 [=============>................] - ETA: 0s - loss: 0.1146 - accuracy: 0.9841 4224/6993 [=================>............] - ETA: 0s - loss: 0.1066 - accuracy: 0.9832 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0942 - accuracy: 0.9842 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0869 - accuracy: 0.9851 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0848 - accuracy: 0.9850 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0835 - accuracy: 0.9846 - val_loss: 0.5543 - val_accuracy: 0.9277 Epoch 98/199 128/6993 [..............................] - ETA: 0s - loss: 0.0024 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0348 - accuracy: 0.9935 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0453 - accuracy: 0.9904 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0564 - accuracy: 0.9881 3328/6993 [=============>................] - ETA: 0s - loss: 0.0674 - accuracy: 0.9853 4096/6993 [================>.............] - ETA: 0s - loss: 0.0896 - accuracy: 0.9832 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0811 - accuracy: 0.9844 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0827 - accuracy: 0.9846 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0787 - accuracy: 0.9851 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0787 - accuracy: 0.9844 - val_loss: 0.5125 - val_accuracy: 0.9216 Epoch 99/199 128/6993 [..............................] - ETA: 0s - loss: 0.0384 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0854 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0692 - accuracy: 0.9856 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0625 - accuracy: 0.9855 3328/6993 [=============>................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9850 4096/6993 [================>.............] - ETA: 0s - loss: 0.0734 - accuracy: 0.9851 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0735 - accuracy: 0.9848 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0721 - accuracy: 0.9852 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0690 - accuracy: 0.9853 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0724 - accuracy: 0.9848 - val_loss: 0.6151 - val_accuracy: 0.9166 Epoch 100/199 128/6993 [..............................] - ETA: 0s - loss: 0.0221 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0339 - accuracy: 0.9902 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0349 - accuracy: 0.9894 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0315 - accuracy: 0.9902 3328/6993 [=============>................] - ETA: 0s - loss: 0.0363 - accuracy: 0.9892 4224/6993 [=================>............] - ETA: 0s - loss: 0.0452 - accuracy: 0.9884 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0513 - accuracy: 0.9878 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0681 - accuracy: 0.9862 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0649 - accuracy: 0.9864 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0661 - accuracy: 0.9860 - val_loss: 0.5280 - val_accuracy: 0.9267 Epoch 101/199 128/6993 [..............................] - ETA: 0s - loss: 0.2614 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.1511 - accuracy: 0.9710 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1414 - accuracy: 0.9732 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1151 - accuracy: 0.9773 3328/6993 [=============>................] - ETA: 0s - loss: 0.1002 - accuracy: 0.9808 4224/6993 [=================>............] - ETA: 0s - loss: 0.0982 - accuracy: 0.9806 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0867 - accuracy: 0.9826 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0842 - accuracy: 0.9832 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0867 - accuracy: 0.9830 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0944 - accuracy: 0.9816 - val_loss: 0.5543 - val_accuracy: 0.9166 Epoch 102/199 128/6993 [..............................] - ETA: 0s - loss: 0.0794 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0442 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0492 - accuracy: 0.9872 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0517 - accuracy: 0.9878 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0442 - accuracy: 0.9893 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0672 - accuracy: 0.9880 4352/6993 [=================>............] - ETA: 0s - loss: 0.0643 - accuracy: 0.9876 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0747 - accuracy: 0.9863 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0718 - accuracy: 0.9872 6784/6993 [============================>.] - ETA: 0s - loss: 0.0702 - accuracy: 0.9870 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0686 - accuracy: 0.9874 - val_loss: 0.5659 - val_accuracy: 0.9216 Epoch 103/199 128/6993 [..............................] - ETA: 0s - loss: 0.0188 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1193 - accuracy: 0.9833 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0850 - accuracy: 0.9821 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0831 - accuracy: 0.9805 3328/6993 [=============>................] - ETA: 0s - loss: 0.0869 - accuracy: 0.9799 3968/6993 [================>.............] - ETA: 0s - loss: 0.0811 - accuracy: 0.9816 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0844 - accuracy: 0.9808 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0828 - accuracy: 0.9809 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0815 - accuracy: 0.9816 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0829 - accuracy: 0.9814 - val_loss: 0.4994 - val_accuracy: 0.9237 Epoch 104/199 128/6993 [..............................] - ETA: 0s - loss: 0.0379 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0454 - accuracy: 0.9933 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0491 - accuracy: 0.9916 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0551 - accuracy: 0.9887 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0597 - accuracy: 0.9862 3456/6993 [=============>................] - ETA: 0s - loss: 0.0691 - accuracy: 0.9858 4096/6993 [================>.............] - ETA: 0s - loss: 0.0688 - accuracy: 0.9846 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0686 - accuracy: 0.9850 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0679 - accuracy: 0.9859 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0647 - accuracy: 0.9867 6912/6993 [============================>.] - ETA: 0s - loss: 0.0658 - accuracy: 0.9864 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0651 - accuracy: 0.9866 - val_loss: 0.5516 - val_accuracy: 0.9181 Epoch 105/199 128/6993 [..............................] - ETA: 0s - loss: 0.0092 - accuracy: 1.0000 640/6993 [=>............................] - ETA: 0s - loss: 0.0743 - accuracy: 0.9859 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0967 - accuracy: 0.9811 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0930 - accuracy: 0.9809 3200/6993 [============>.................] - ETA: 0s - loss: 0.0743 - accuracy: 0.9847 3968/6993 [================>.............] - ETA: 0s - loss: 0.0767 - accuracy: 0.9851 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0724 - accuracy: 0.9854 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0683 - accuracy: 0.9853 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0743 - accuracy: 0.9834 6993/6993 [==============================] - 1s 81us/sample - loss: 0.0745 - accuracy: 0.9840 - val_loss: 0.5797 - val_accuracy: 0.9257 Epoch 106/199 128/6993 [..............................] - ETA: 0s - loss: 0.0091 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0450 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0460 - accuracy: 0.9866 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0567 - accuracy: 0.9859 3328/6993 [=============>................] - ETA: 0s - loss: 0.0579 - accuracy: 0.9868 4096/6993 [================>.............] - ETA: 0s - loss: 0.0597 - accuracy: 0.9858 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0608 - accuracy: 0.9856 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0631 - accuracy: 0.9847 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0616 - accuracy: 0.9850 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0596 - accuracy: 0.9848 - val_loss: 0.6197 - val_accuracy: 0.9221 Epoch 107/199 128/6993 [..............................] - ETA: 0s - loss: 0.0104 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0884 - accuracy: 0.9821 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0783 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0850 - accuracy: 0.9832 3456/6993 [=============>................] - ETA: 0s - loss: 0.0745 - accuracy: 0.9850 4224/6993 [=================>............] - ETA: 0s - loss: 0.0750 - accuracy: 0.9853 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0729 - accuracy: 0.9848 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0727 - accuracy: 0.9840 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0741 - accuracy: 0.9835 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0730 - accuracy: 0.9837 - val_loss: 0.5545 - val_accuracy: 0.9277 Epoch 108/199 128/6993 [..............................] - ETA: 0s - loss: 0.0258 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0688 - accuracy: 0.9863 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0522 - accuracy: 0.9877 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0528 - accuracy: 0.9879 3328/6993 [=============>................] - ETA: 0s - loss: 0.0515 - accuracy: 0.9889 4224/6993 [=================>............] - ETA: 0s - loss: 0.0620 - accuracy: 0.9879 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0617 - accuracy: 0.9872 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0565 - accuracy: 0.9878 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0537 - accuracy: 0.9881 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0612 - accuracy: 0.9878 - val_loss: 0.4969 - val_accuracy: 0.9257 Epoch 109/199 128/6993 [..............................] - ETA: 0s - loss: 0.0112 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0871 - accuracy: 0.9944 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0966 - accuracy: 0.9898 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0806 - accuracy: 0.9891 3328/6993 [=============>................] - ETA: 0s - loss: 0.0733 - accuracy: 0.9895 4096/6993 [================>.............] - ETA: 0s - loss: 0.0705 - accuracy: 0.9878 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0747 - accuracy: 0.9864 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0734 - accuracy: 0.9861 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0697 - accuracy: 0.9867 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0661 - accuracy: 0.9871 - val_loss: 0.5248 - val_accuracy: 0.9257 Epoch 110/199 128/6993 [..............................] - ETA: 0s - loss: 0.0586 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0391 - accuracy: 0.9911 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0508 - accuracy: 0.9898 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0543 - accuracy: 0.9887 3328/6993 [=============>................] - ETA: 0s - loss: 0.0526 - accuracy: 0.9886 4096/6993 [================>.............] - ETA: 0s - loss: 0.0581 - accuracy: 0.9878 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0607 - accuracy: 0.9883 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0646 - accuracy: 0.9869 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0701 - accuracy: 0.9862 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0727 - accuracy: 0.9863 - val_loss: 0.4771 - val_accuracy: 0.9262 Epoch 111/199 128/6993 [..............................] - ETA: 0s - loss: 0.0131 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0667 - accuracy: 0.9844 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0530 - accuracy: 0.9870 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0525 - accuracy: 0.9871 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0592 - accuracy: 0.9864 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0566 - accuracy: 0.9865 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0529 - accuracy: 0.9876 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0554 - accuracy: 0.9874 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0586 - accuracy: 0.9871 6912/6993 [============================>.] - ETA: 0s - loss: 0.0619 - accuracy: 0.9864 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0615 - accuracy: 0.9863 - val_loss: 0.6931 - val_accuracy: 0.9176 Epoch 112/199 128/6993 [..............................] - ETA: 0s - loss: 0.0909 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0727 - accuracy: 0.9900 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0808 - accuracy: 0.9833 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0869 - accuracy: 0.9844 3328/6993 [=============>................] - ETA: 0s - loss: 0.0853 - accuracy: 0.9844 4224/6993 [=================>............] - ETA: 0s - loss: 0.0816 - accuracy: 0.9848 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0903 - accuracy: 0.9850 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0877 - accuracy: 0.9851 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0876 - accuracy: 0.9839 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0910 - accuracy: 0.9841 - val_loss: 0.5404 - val_accuracy: 0.9292 Epoch 113/199 128/6993 [..............................] - ETA: 0s - loss: 0.0678 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1219 - accuracy: 0.9810 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1028 - accuracy: 0.9798 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0972 - accuracy: 0.9814 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1115 - accuracy: 0.9812 3072/6993 [============>.................] - ETA: 0s - loss: 0.1024 - accuracy: 0.9824 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0930 - accuracy: 0.9838 4096/6993 [================>.............] - ETA: 0s - loss: 0.0854 - accuracy: 0.9849 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0801 - accuracy: 0.9852 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0773 - accuracy: 0.9852 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0767 - accuracy: 0.9851 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0781 - accuracy: 0.9842 6912/6993 [============================>.] - ETA: 0s - loss: 0.0781 - accuracy: 0.9835 6993/6993 [==============================] - 1s 111us/sample - loss: 0.0774 - accuracy: 0.9836 - val_loss: 0.5223 - val_accuracy: 0.9267 Epoch 114/199 128/6993 [..............................] - ETA: 0s - loss: 0.0036 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0333 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0483 - accuracy: 0.9886 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0484 - accuracy: 0.9877 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0600 - accuracy: 0.9856 3072/6993 [============>.................] - ETA: 0s - loss: 0.0548 - accuracy: 0.9870 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0540 - accuracy: 0.9867 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0554 - accuracy: 0.9862 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0531 - accuracy: 0.9859 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0596 - accuracy: 0.9844 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0627 - accuracy: 0.9848 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0617 - accuracy: 0.9848 - val_loss: 0.5516 - val_accuracy: 0.9272 Epoch 115/199 128/6993 [..............................] - ETA: 0s - loss: 0.0248 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0391 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0475 - accuracy: 0.9851 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0642 - accuracy: 0.9839 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0720 - accuracy: 0.9840 3200/6993 [============>.................] - ETA: 0s - loss: 0.0718 - accuracy: 0.9850 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0679 - accuracy: 0.9862 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0652 - accuracy: 0.9863 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0637 - accuracy: 0.9856 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0737 - accuracy: 0.9847 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0706 - accuracy: 0.9847 - val_loss: 0.5706 - val_accuracy: 0.9237 Epoch 116/199 128/6993 [..............................] - ETA: 0s - loss: 0.0911 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0543 - accuracy: 0.9857 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0488 - accuracy: 0.9852 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0491 - accuracy: 0.9849 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0496 - accuracy: 0.9861 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0560 - accuracy: 0.9862 3328/6993 [=============>................] - ETA: 0s - loss: 0.0615 - accuracy: 0.9850 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0642 - accuracy: 0.9844 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0611 - accuracy: 0.9848 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0640 - accuracy: 0.9844 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0607 - accuracy: 0.9847 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0621 - accuracy: 0.9847 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0595 - accuracy: 0.9853 6993/6993 [==============================] - 1s 109us/sample - loss: 0.0586 - accuracy: 0.9854 - val_loss: 0.6319 - val_accuracy: 0.9196 Epoch 117/199 128/6993 [..............................] - ETA: 0s - loss: 0.1272 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0593 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0444 - accuracy: 0.9922 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0462 - accuracy: 0.9922 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0638 - accuracy: 0.9913 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0652 - accuracy: 0.9904 3328/6993 [=============>................] - ETA: 0s - loss: 0.0624 - accuracy: 0.9898 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0607 - accuracy: 0.9893 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0606 - accuracy: 0.9895 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0678 - accuracy: 0.9883 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0718 - accuracy: 0.9869 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0737 - accuracy: 0.9868 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0752 - accuracy: 0.9866 6993/6993 [==============================] - 1s 109us/sample - loss: 0.0744 - accuracy: 0.9868 - val_loss: 0.6680 - val_accuracy: 0.9211 Epoch 118/199 128/6993 [..............................] - ETA: 0s - loss: 0.0659 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.1075 - accuracy: 0.9828 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1020 - accuracy: 0.9844 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0837 - accuracy: 0.9839 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0737 - accuracy: 0.9847 3328/6993 [=============>................] - ETA: 0s - loss: 0.0807 - accuracy: 0.9829 3968/6993 [================>.............] - ETA: 0s - loss: 0.0764 - accuracy: 0.9836 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0755 - accuracy: 0.9833 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0720 - accuracy: 0.9838 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0811 - accuracy: 0.9842 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0798 - accuracy: 0.9844 6784/6993 [============================>.] - ETA: 0s - loss: 0.0802 - accuracy: 0.9841 6993/6993 [==============================] - 1s 109us/sample - loss: 0.0790 - accuracy: 0.9843 - val_loss: 0.6040 - val_accuracy: 0.9186 Epoch 119/199 128/6993 [..............................] - ETA: 1s - loss: 0.0606 - accuracy: 0.9844 512/6993 [=>............................] - ETA: 1s - loss: 0.0272 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 1s - loss: 0.0526 - accuracy: 0.9888 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0475 - accuracy: 0.9908 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0652 - accuracy: 0.9875 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0632 - accuracy: 0.9870 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0544 - accuracy: 0.9879 3328/6993 [=============>................] - ETA: 0s - loss: 0.0512 - accuracy: 0.9883 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0511 - accuracy: 0.9872 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0491 - accuracy: 0.9879 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0525 - accuracy: 0.9878 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0528 - accuracy: 0.9880 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0527 - accuracy: 0.9880 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0517 - accuracy: 0.9881 6784/6993 [============================>.] - ETA: 0s - loss: 0.0633 - accuracy: 0.9881 6993/6993 [==============================] - 1s 138us/sample - loss: 0.0626 - accuracy: 0.9883 - val_loss: 0.6613 - val_accuracy: 0.9232 Epoch 120/199 128/6993 [..............................] - ETA: 0s - loss: 0.0850 - accuracy: 0.9922 512/6993 [=>............................] - ETA: 0s - loss: 0.0463 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0360 - accuracy: 0.9933 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0443 - accuracy: 0.9913 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0512 - accuracy: 0.9883 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0503 - accuracy: 0.9880 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0690 - accuracy: 0.9870 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0724 - accuracy: 0.9875 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0693 - accuracy: 0.9878 3328/6993 [=============>................] - ETA: 0s - loss: 0.0771 - accuracy: 0.9868 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0748 - accuracy: 0.9869 3968/6993 [================>.............] - ETA: 0s - loss: 0.0706 - accuracy: 0.9871 4352/6993 [=================>............] - ETA: 0s - loss: 0.0683 - accuracy: 0.9874 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0673 - accuracy: 0.9873 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0690 - accuracy: 0.9866 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0683 - accuracy: 0.9866 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0688 - accuracy: 0.9866 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0735 - accuracy: 0.9870 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0753 - accuracy: 0.9862 6993/6993 [==============================] - 1s 172us/sample - loss: 0.0738 - accuracy: 0.9863 - val_loss: 0.5955 - val_accuracy: 0.9252 Epoch 121/199 128/6993 [..............................] - ETA: 0s - loss: 0.1059 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.1101 - accuracy: 0.9859 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0766 - accuracy: 0.9870 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0838 - accuracy: 0.9868 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0730 - accuracy: 0.9883 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0845 - accuracy: 0.9867 3072/6993 [============>.................] - ETA: 0s - loss: 0.0788 - accuracy: 0.9854 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0782 - accuracy: 0.9855 4096/6993 [================>.............] - ETA: 0s - loss: 0.0745 - accuracy: 0.9861 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0805 - accuracy: 0.9852 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0757 - accuracy: 0.9859 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0789 - accuracy: 0.9858 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0760 - accuracy: 0.9857 6912/6993 [============================>.] - ETA: 0s - loss: 0.0734 - accuracy: 0.9860 6993/6993 [==============================] - 1s 113us/sample - loss: 0.0728 - accuracy: 0.9860 - val_loss: 0.5744 - val_accuracy: 0.9237 Epoch 122/199 128/6993 [..............................] - ETA: 1s - loss: 0.1493 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0690 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0645 - accuracy: 0.9872 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0598 - accuracy: 0.9873 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0576 - accuracy: 0.9871 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0571 - accuracy: 0.9876 4352/6993 [=================>............] - ETA: 0s - loss: 0.0700 - accuracy: 0.9864 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0691 - accuracy: 0.9864 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0706 - accuracy: 0.9862 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0767 - accuracy: 0.9859 6912/6993 [============================>.] - ETA: 0s - loss: 0.0786 - accuracy: 0.9858 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0808 - accuracy: 0.9857 - val_loss: 0.6545 - val_accuracy: 0.9151 Epoch 123/199 128/6993 [..............................] - ETA: 0s - loss: 0.0116 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0200 - accuracy: 0.9961 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0554 - accuracy: 0.9844 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0454 - accuracy: 0.9863 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0438 - accuracy: 0.9859 3456/6993 [=============>................] - ETA: 0s - loss: 0.0520 - accuracy: 0.9855 4096/6993 [================>.............] - ETA: 0s - loss: 0.0630 - accuracy: 0.9849 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0585 - accuracy: 0.9856 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0574 - accuracy: 0.9859 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0544 - accuracy: 0.9864 6784/6993 [============================>.] - ETA: 0s - loss: 0.0607 - accuracy: 0.9857 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0621 - accuracy: 0.9858 - val_loss: 0.5812 - val_accuracy: 0.9146 Epoch 124/199 128/6993 [..............................] - ETA: 0s - loss: 0.0262 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0375 - accuracy: 0.9896 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0555 - accuracy: 0.9863 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0539 - accuracy: 0.9865 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0567 - accuracy: 0.9868 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0638 - accuracy: 0.9863 4352/6993 [=================>............] - ETA: 0s - loss: 0.0586 - accuracy: 0.9874 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0647 - accuracy: 0.9867 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0769 - accuracy: 0.9860 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0726 - accuracy: 0.9868 6912/6993 [============================>.] - ETA: 0s - loss: 0.0713 - accuracy: 0.9861 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0737 - accuracy: 0.9858 - val_loss: 0.6538 - val_accuracy: 0.9105 Epoch 125/199 128/6993 [..............................] - ETA: 0s - loss: 0.0802 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.0565 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0639 - accuracy: 0.9865 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0732 - accuracy: 0.9844 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0712 - accuracy: 0.9858 3456/6993 [=============>................] - ETA: 0s - loss: 0.0623 - accuracy: 0.9878 4096/6993 [================>.............] - ETA: 0s - loss: 0.0593 - accuracy: 0.9878 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0552 - accuracy: 0.9882 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0573 - accuracy: 0.9883 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0544 - accuracy: 0.9885 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0611 - accuracy: 0.9870 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0629 - accuracy: 0.9865 6912/6993 [============================>.] - ETA: 0s - loss: 0.0662 - accuracy: 0.9868 6993/6993 [==============================] - 1s 112us/sample - loss: 0.0671 - accuracy: 0.9868 - val_loss: 0.6714 - val_accuracy: 0.9196 Epoch 126/199 128/6993 [..............................] - ETA: 0s - loss: 0.0287 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.0392 - accuracy: 0.9875 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0606 - accuracy: 0.9844 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0566 - accuracy: 0.9859 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0608 - accuracy: 0.9863 3200/6993 [============>.................] - ETA: 0s - loss: 0.0542 - accuracy: 0.9878 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0555 - accuracy: 0.9867 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0513 - accuracy: 0.9875 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0607 - accuracy: 0.9875 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0589 - accuracy: 0.9873 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0626 - accuracy: 0.9875 6912/6993 [============================>.] - ETA: 0s - loss: 0.0639 - accuracy: 0.9870 6993/6993 [==============================] - 1s 101us/sample - loss: 0.0635 - accuracy: 0.9870 - val_loss: 0.6218 - val_accuracy: 0.9211 Epoch 127/199 128/6993 [..............................] - ETA: 1s - loss: 0.0416 - accuracy: 0.9844 512/6993 [=>............................] - ETA: 1s - loss: 0.1372 - accuracy: 0.9824 896/6993 [==>...........................] - ETA: 1s - loss: 0.0947 - accuracy: 0.9855 1280/6993 [====>.........................] - ETA: 1s - loss: 0.1257 - accuracy: 0.9828 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1000 - accuracy: 0.9838 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0917 - accuracy: 0.9858 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0832 - accuracy: 0.9859 3200/6993 [============>.................] - ETA: 0s - loss: 0.0764 - accuracy: 0.9866 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0787 - accuracy: 0.9865 4224/6993 [=================>............] - ETA: 0s - loss: 0.0942 - accuracy: 0.9858 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0875 - accuracy: 0.9867 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0868 - accuracy: 0.9861 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0823 - accuracy: 0.9865 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0796 - accuracy: 0.9870 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0821 - accuracy: 0.9868 6993/6993 [==============================] - 1s 147us/sample - loss: 0.0818 - accuracy: 0.9864 - val_loss: 0.5618 - val_accuracy: 0.9171 Epoch 128/199 128/6993 [..............................] - ETA: 0s - loss: 0.2014 - accuracy: 0.9844 512/6993 [=>............................] - ETA: 0s - loss: 0.0972 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0876 - accuracy: 0.9854 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0885 - accuracy: 0.9838 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0794 - accuracy: 0.9863 3200/6993 [============>.................] - ETA: 0s - loss: 0.0782 - accuracy: 0.9866 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0727 - accuracy: 0.9872 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0769 - accuracy: 0.9848 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0800 - accuracy: 0.9846 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0841 - accuracy: 0.9845 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0820 - accuracy: 0.9847 6912/6993 [============================>.] - ETA: 0s - loss: 0.0842 - accuracy: 0.9838 6993/6993 [==============================] - 1s 102us/sample - loss: 0.0835 - accuracy: 0.9838 - val_loss: 0.5370 - val_accuracy: 0.9201 Epoch 129/199 128/6993 [..............................] - ETA: 1s - loss: 0.0937 - accuracy: 0.9688 384/6993 [>.............................] - ETA: 1s - loss: 0.0943 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 1s - loss: 0.0686 - accuracy: 0.9818 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0706 - accuracy: 0.9828 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0743 - accuracy: 0.9826 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0671 - accuracy: 0.9839 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0707 - accuracy: 0.9840 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9851 3328/6993 [=============>................] - ETA: 0s - loss: 0.0702 - accuracy: 0.9856 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0671 - accuracy: 0.9862 4224/6993 [=================>............] - ETA: 0s - loss: 0.0620 - accuracy: 0.9872 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0638 - accuracy: 0.9878 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0734 - accuracy: 0.9868 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0731 - accuracy: 0.9870 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0811 - accuracy: 0.9874 6993/6993 [==============================] - 1s 133us/sample - loss: 0.0858 - accuracy: 0.9874 - val_loss: 0.5959 - val_accuracy: 0.9211 Epoch 130/199 128/6993 [..............................] - ETA: 0s - loss: 0.0425 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0636 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0725 - accuracy: 0.9858 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0688 - accuracy: 0.9849 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0713 - accuracy: 0.9852 3072/6993 [============>.................] - ETA: 0s - loss: 0.0705 - accuracy: 0.9850 3456/6993 [=============>................] - ETA: 0s - loss: 0.0648 - accuracy: 0.9858 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0791 - accuracy: 0.9844 4224/6993 [=================>............] - ETA: 0s - loss: 0.0738 - accuracy: 0.9851 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0708 - accuracy: 0.9855 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0721 - accuracy: 0.9854 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0734 - accuracy: 0.9849 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0742 - accuracy: 0.9844 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0749 - accuracy: 0.9852 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0743 - accuracy: 0.9854 6993/6993 [==============================] - 1s 143us/sample - loss: 0.0729 - accuracy: 0.9850 - val_loss: 0.5268 - val_accuracy: 0.9257 Epoch 131/199 128/6993 [..............................] - ETA: 0s - loss: 0.0596 - accuracy: 0.9844 512/6993 [=>............................] - ETA: 0s - loss: 0.1033 - accuracy: 0.9785 896/6993 [==>...........................] - ETA: 0s - loss: 0.0742 - accuracy: 0.9833 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0512 - accuracy: 0.9879 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0717 - accuracy: 0.9849 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0833 - accuracy: 0.9848 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0798 - accuracy: 0.9869 3328/6993 [=============>................] - ETA: 0s - loss: 0.0768 - accuracy: 0.9874 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0734 - accuracy: 0.9872 4352/6993 [=================>............] - ETA: 0s - loss: 0.0743 - accuracy: 0.9874 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0714 - accuracy: 0.9870 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0772 - accuracy: 0.9859 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0761 - accuracy: 0.9857 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0761 - accuracy: 0.9861 6784/6993 [============================>.] - ETA: 0s - loss: 0.0758 - accuracy: 0.9860 6993/6993 [==============================] - 1s 134us/sample - loss: 0.0766 - accuracy: 0.9860 - val_loss: 0.5837 - val_accuracy: 0.9191 Epoch 132/199 128/6993 [..............................] - ETA: 0s - loss: 0.1880 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0878 - accuracy: 0.9855 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0617 - accuracy: 0.9870 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0694 - accuracy: 0.9878 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0627 - accuracy: 0.9874 3328/6993 [=============>................] - ETA: 0s - loss: 0.0588 - accuracy: 0.9859 3968/6993 [================>.............] - ETA: 0s - loss: 0.0606 - accuracy: 0.9869 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0786 - accuracy: 0.9854 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0804 - accuracy: 0.9849 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0809 - accuracy: 0.9844 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0783 - accuracy: 0.9848 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0755 - accuracy: 0.9851 - val_loss: 0.6081 - val_accuracy: 0.9181 Epoch 133/199 128/6993 [..............................] - ETA: 0s - loss: 0.0309 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0896 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0595 - accuracy: 0.9915 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0623 - accuracy: 0.9897 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0520 - accuracy: 0.9911 3328/6993 [=============>................] - ETA: 0s - loss: 0.0558 - accuracy: 0.9910 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0509 - accuracy: 0.9911 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0518 - accuracy: 0.9906 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0549 - accuracy: 0.9896 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0587 - accuracy: 0.9894 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0576 - accuracy: 0.9891 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0539 - accuracy: 0.9896 - val_loss: 0.7194 - val_accuracy: 0.9211 Epoch 134/199 128/6993 [..............................] - ETA: 0s - loss: 0.0504 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1158 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0756 - accuracy: 0.9893 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0599 - accuracy: 0.9907 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0538 - accuracy: 0.9914 3200/6993 [============>.................] - ETA: 0s - loss: 0.0722 - accuracy: 0.9897 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0857 - accuracy: 0.9884 4224/6993 [=================>............] - ETA: 0s - loss: 0.0784 - accuracy: 0.9889 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0810 - accuracy: 0.9882 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0770 - accuracy: 0.9885 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0725 - accuracy: 0.9886 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0702 - accuracy: 0.9881 6993/6993 [==============================] - 1s 106us/sample - loss: 0.0695 - accuracy: 0.9874 - val_loss: 0.6405 - val_accuracy: 0.9242 Epoch 135/199 128/6993 [..............................] - ETA: 1s - loss: 0.0083 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0292 - accuracy: 0.9948 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0264 - accuracy: 0.9943 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0580 - accuracy: 0.9878 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0501 - accuracy: 0.9892 3328/6993 [=============>................] - ETA: 0s - loss: 0.0516 - accuracy: 0.9898 3968/6993 [================>.............] - ETA: 0s - loss: 0.0657 - accuracy: 0.9887 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0615 - accuracy: 0.9889 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0596 - accuracy: 0.9891 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0551 - accuracy: 0.9898 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0739 - accuracy: 0.9884 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0754 - accuracy: 0.9878 - val_loss: 0.6944 - val_accuracy: 0.9191 Epoch 136/199 128/6993 [..............................] - ETA: 0s - loss: 0.0393 - accuracy: 0.9922 512/6993 [=>............................] - ETA: 0s - loss: 0.0505 - accuracy: 0.9863 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0755 - accuracy: 0.9870 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0680 - accuracy: 0.9874 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0658 - accuracy: 0.9883 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0687 - accuracy: 0.9874 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0701 - accuracy: 0.9869 4224/6993 [=================>............] - ETA: 0s - loss: 0.0627 - accuracy: 0.9882 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0604 - accuracy: 0.9885 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0569 - accuracy: 0.9886 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0581 - accuracy: 0.9881 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0642 - accuracy: 0.9874 6993/6993 [==============================] - 1s 102us/sample - loss: 0.0631 - accuracy: 0.9874 - val_loss: 0.6582 - val_accuracy: 0.9201 Epoch 137/199 128/6993 [..............................] - ETA: 0s - loss: 0.2556 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.1284 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0955 - accuracy: 0.9851 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0757 - accuracy: 0.9871 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0803 - accuracy: 0.9858 3456/6993 [=============>................] - ETA: 0s - loss: 0.1012 - accuracy: 0.9852 4096/6993 [================>.............] - ETA: 0s - loss: 0.0987 - accuracy: 0.9858 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0957 - accuracy: 0.9861 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0898 - accuracy: 0.9859 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0835 - accuracy: 0.9859 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0808 - accuracy: 0.9862 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0783 - accuracy: 0.9861 - val_loss: 0.6977 - val_accuracy: 0.9277 Epoch 138/199 128/6993 [..............................] - ETA: 0s - loss: 0.0665 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0533 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0560 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0651 - accuracy: 0.9858 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0607 - accuracy: 0.9854 3456/6993 [=============>................] - ETA: 0s - loss: 0.0627 - accuracy: 0.9850 4096/6993 [================>.............] - ETA: 0s - loss: 0.0649 - accuracy: 0.9858 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0643 - accuracy: 0.9863 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0627 - accuracy: 0.9862 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0603 - accuracy: 0.9869 6784/6993 [============================>.] - ETA: 0s - loss: 0.0624 - accuracy: 0.9872 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0613 - accuracy: 0.9874 - val_loss: 0.6845 - val_accuracy: 0.9216 Epoch 139/199 128/6993 [..............................] - ETA: 0s - loss: 0.0020 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0254 - accuracy: 0.9974 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0572 - accuracy: 0.9908 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0518 - accuracy: 0.9907 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0687 - accuracy: 0.9883 3072/6993 [============>.................] - ETA: 0s - loss: 0.0892 - accuracy: 0.9857 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0912 - accuracy: 0.9857 4352/6993 [=================>............] - ETA: 0s - loss: 0.0939 - accuracy: 0.9853 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0922 - accuracy: 0.9846 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0864 - accuracy: 0.9849 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0856 - accuracy: 0.9849 6912/6993 [============================>.] - ETA: 0s - loss: 0.0817 - accuracy: 0.9851 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0810 - accuracy: 0.9851 - val_loss: 0.6389 - val_accuracy: 0.9171 Epoch 140/199 128/6993 [..............................] - ETA: 0s - loss: 0.0709 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.0448 - accuracy: 0.9828 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0329 - accuracy: 0.9878 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0568 - accuracy: 0.9872 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0736 - accuracy: 0.9856 3072/6993 [============>.................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9870 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0803 - accuracy: 0.9865 4352/6993 [=================>............] - ETA: 0s - loss: 0.0855 - accuracy: 0.9862 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0920 - accuracy: 0.9852 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0901 - accuracy: 0.9849 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0857 - accuracy: 0.9853 6912/6993 [============================>.] - ETA: 0s - loss: 0.0833 - accuracy: 0.9858 6993/6993 [==============================] - 1s 99us/sample - loss: 0.0836 - accuracy: 0.9856 - val_loss: 0.6224 - val_accuracy: 0.9232 Epoch 141/199 128/6993 [..............................] - ETA: 0s - loss: 0.0803 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.1066 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1209 - accuracy: 0.9837 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1451 - accuracy: 0.9830 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1493 - accuracy: 0.9830 3456/6993 [=============>................] - ETA: 0s - loss: 0.1259 - accuracy: 0.9847 4096/6993 [================>.............] - ETA: 0s - loss: 0.1159 - accuracy: 0.9846 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1057 - accuracy: 0.9854 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0995 - accuracy: 0.9853 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0947 - accuracy: 0.9852 6784/6993 [============================>.] - ETA: 0s - loss: 0.0975 - accuracy: 0.9847 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0974 - accuracy: 0.9841 - val_loss: 0.5785 - val_accuracy: 0.9252 Epoch 142/199 128/6993 [..............................] - ETA: 0s - loss: 0.0155 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0195 - accuracy: 0.9944 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0299 - accuracy: 0.9928 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0484 - accuracy: 0.9913 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0478 - accuracy: 0.9918 3328/6993 [=============>................] - ETA: 0s - loss: 0.0614 - accuracy: 0.9913 3968/6993 [================>.............] - ETA: 0s - loss: 0.0579 - accuracy: 0.9914 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0570 - accuracy: 0.9906 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0596 - accuracy: 0.9908 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0632 - accuracy: 0.9906 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0642 - accuracy: 0.9897 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0631 - accuracy: 0.9890 6993/6993 [==============================] - 1s 108us/sample - loss: 0.0633 - accuracy: 0.9891 - val_loss: 0.5767 - val_accuracy: 0.9307 Epoch 143/199 128/6993 [..............................] - ETA: 0s - loss: 0.0183 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0236 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0409 - accuracy: 0.9901 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0625 - accuracy: 0.9862 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0643 - accuracy: 0.9865 3456/6993 [=============>................] - ETA: 0s - loss: 0.0570 - accuracy: 0.9881 4096/6993 [================>.............] - ETA: 0s - loss: 0.0580 - accuracy: 0.9873 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0635 - accuracy: 0.9865 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0630 - accuracy: 0.9862 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0608 - accuracy: 0.9855 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0587 - accuracy: 0.9860 6993/6993 [==============================] - 1s 97us/sample - loss: 0.0571 - accuracy: 0.9866 - val_loss: 0.7635 - val_accuracy: 0.9242 Epoch 144/199 128/6993 [..............................] - ETA: 0s - loss: 0.0515 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0471 - accuracy: 0.9870 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0433 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0500 - accuracy: 0.9893 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0576 - accuracy: 0.9892 3328/6993 [=============>................] - ETA: 0s - loss: 0.0600 - accuracy: 0.9892 3968/6993 [================>.............] - ETA: 0s - loss: 0.0596 - accuracy: 0.9892 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0604 - accuracy: 0.9891 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0571 - accuracy: 0.9893 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0570 - accuracy: 0.9893 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0537 - accuracy: 0.9896 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0533 - accuracy: 0.9894 - val_loss: 0.7609 - val_accuracy: 0.9191 Epoch 145/199 128/6993 [..............................] - ETA: 0s - loss: 0.0064 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0240 - accuracy: 0.9961 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0458 - accuracy: 0.9893 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0367 - accuracy: 0.9907 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0490 - accuracy: 0.9898 3200/6993 [============>.................] - ETA: 0s - loss: 0.0615 - accuracy: 0.9894 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0591 - accuracy: 0.9898 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0569 - accuracy: 0.9897 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0573 - accuracy: 0.9898 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0687 - accuracy: 0.9892 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0684 - accuracy: 0.9891 6912/6993 [============================>.] - ETA: 0s - loss: 0.0668 - accuracy: 0.9890 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0660 - accuracy: 0.9891 - val_loss: 0.8144 - val_accuracy: 0.9226 Epoch 146/199 128/6993 [..............................] - ETA: 0s - loss: 0.0121 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0182 - accuracy: 0.9944 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0584 - accuracy: 0.9896 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0741 - accuracy: 0.9881 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0766 - accuracy: 0.9886 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0660 - accuracy: 0.9888 4224/6993 [=================>............] - ETA: 0s - loss: 0.0700 - accuracy: 0.9886 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0692 - accuracy: 0.9883 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0681 - accuracy: 0.9875 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0834 - accuracy: 0.9865 6784/6993 [============================>.] - ETA: 0s - loss: 0.0814 - accuracy: 0.9863 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0835 - accuracy: 0.9858 - val_loss: 0.7278 - val_accuracy: 0.9125 Epoch 147/199 128/6993 [..............................] - ETA: 1s - loss: 0.0279 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0853 - accuracy: 0.9818 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1064 - accuracy: 0.9794 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1043 - accuracy: 0.9839 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0900 - accuracy: 0.9851 3456/6993 [=============>................] - ETA: 0s - loss: 0.0974 - accuracy: 0.9850 4096/6993 [================>.............] - ETA: 0s - loss: 0.0893 - accuracy: 0.9856 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0892 - accuracy: 0.9859 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0859 - accuracy: 0.9862 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0879 - accuracy: 0.9859 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0876 - accuracy: 0.9853 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0865 - accuracy: 0.9856 - val_loss: 0.6302 - val_accuracy: 0.9257 Epoch 148/199 128/6993 [..............................] - ETA: 0s - loss: 0.0804 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.0531 - accuracy: 0.9891 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0378 - accuracy: 0.9913 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0393 - accuracy: 0.9910 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0328 - accuracy: 0.9926 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0301 - accuracy: 0.9929 3200/6993 [============>.................] - ETA: 0s - loss: 0.0316 - accuracy: 0.9931 3968/6993 [================>.............] - ETA: 0s - loss: 0.0473 - accuracy: 0.9902 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0669 - accuracy: 0.9894 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0707 - accuracy: 0.9888 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0784 - accuracy: 0.9883 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0770 - accuracy: 0.9874 6993/6993 [==============================] - 1s 104us/sample - loss: 0.0741 - accuracy: 0.9874 - val_loss: 0.6618 - val_accuracy: 0.9226 Epoch 149/199 128/6993 [..............................] - ETA: 0s - loss: 0.0345 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0692 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0504 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0559 - accuracy: 0.9897 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0519 - accuracy: 0.9896 3328/6993 [=============>................] - ETA: 0s - loss: 0.0522 - accuracy: 0.9892 3968/6993 [================>.............] - ETA: 0s - loss: 0.0618 - accuracy: 0.9882 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0594 - accuracy: 0.9887 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0641 - accuracy: 0.9878 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0702 - accuracy: 0.9869 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0680 - accuracy: 0.9868 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0675 - accuracy: 0.9871 - val_loss: 0.6281 - val_accuracy: 0.9307 Epoch 150/199 128/6993 [..............................] - ETA: 0s - loss: 0.0165 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0711 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0691 - accuracy: 0.9879 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0580 - accuracy: 0.9897 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0654 - accuracy: 0.9903 3072/6993 [============>.................] - ETA: 0s - loss: 0.0669 - accuracy: 0.9896 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0654 - accuracy: 0.9877 4096/6993 [================>.............] - ETA: 0s - loss: 0.0610 - accuracy: 0.9888 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0673 - accuracy: 0.9876 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0663 - accuracy: 0.9877 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0788 - accuracy: 0.9874 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0808 - accuracy: 0.9875 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0837 - accuracy: 0.9877 6993/6993 [==============================] - 1s 107us/sample - loss: 0.0921 - accuracy: 0.9874 - val_loss: 0.6731 - val_accuracy: 0.9242 Epoch 151/199 128/6993 [..............................] - ETA: 1s - loss: 0.0401 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0488 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0800 - accuracy: 0.9851 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0729 - accuracy: 0.9858 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0700 - accuracy: 0.9862 3328/6993 [=============>................] - ETA: 0s - loss: 0.0812 - accuracy: 0.9859 3968/6993 [================>.............] - ETA: 0s - loss: 0.0812 - accuracy: 0.9849 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0770 - accuracy: 0.9848 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0718 - accuracy: 0.9853 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0708 - accuracy: 0.9856 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0710 - accuracy: 0.9854 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0681 - accuracy: 0.9857 - val_loss: 0.6150 - val_accuracy: 0.9252 Epoch 152/199 128/6993 [..............................] - ETA: 0s - loss: 0.0776 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0390 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0979 - accuracy: 0.9872 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1182 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1012 - accuracy: 0.9847 3456/6993 [=============>................] - ETA: 0s - loss: 0.0837 - accuracy: 0.9864 4096/6993 [================>.............] - ETA: 0s - loss: 0.0891 - accuracy: 0.9868 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0955 - accuracy: 0.9863 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0945 - accuracy: 0.9860 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0964 - accuracy: 0.9854 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0931 - accuracy: 0.9853 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0902 - accuracy: 0.9850 - val_loss: 0.6068 - val_accuracy: 0.9272 Epoch 153/199 128/6993 [..............................] - ETA: 0s - loss: 0.1647 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0562 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0372 - accuracy: 0.9922 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0467 - accuracy: 0.9907 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0558 - accuracy: 0.9892 3328/6993 [=============>................] - ETA: 0s - loss: 0.0541 - accuracy: 0.9901 3968/6993 [================>.............] - ETA: 0s - loss: 0.0522 - accuracy: 0.9902 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0506 - accuracy: 0.9902 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0553 - accuracy: 0.9893 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0515 - accuracy: 0.9893 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0567 - accuracy: 0.9891 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0550 - accuracy: 0.9891 - val_loss: 0.7808 - val_accuracy: 0.9201 Epoch 154/199 128/6993 [..............................] - ETA: 0s - loss: 0.0758 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0777 - accuracy: 0.9883 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0617 - accuracy: 0.9915 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0640 - accuracy: 0.9908 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0658 - accuracy: 0.9898 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0740 - accuracy: 0.9894 4352/6993 [=================>............] - ETA: 0s - loss: 0.0817 - accuracy: 0.9887 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0743 - accuracy: 0.9888 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0904 - accuracy: 0.9869 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0917 - accuracy: 0.9863 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0947 - accuracy: 0.9857 - val_loss: 0.6821 - val_accuracy: 0.9181 Epoch 155/199 128/6993 [..............................] - ETA: 0s - loss: 0.0866 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0573 - accuracy: 0.9870 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0616 - accuracy: 0.9837 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0677 - accuracy: 0.9863 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0719 - accuracy: 0.9848 3072/6993 [============>.................] - ETA: 0s - loss: 0.0660 - accuracy: 0.9860 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0630 - accuracy: 0.9857 4224/6993 [=================>............] - ETA: 0s - loss: 0.0778 - accuracy: 0.9839 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0753 - accuracy: 0.9844 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0708 - accuracy: 0.9855 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0674 - accuracy: 0.9860 6784/6993 [============================>.] - ETA: 0s - loss: 0.0684 - accuracy: 0.9858 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0686 - accuracy: 0.9858 - val_loss: 0.6653 - val_accuracy: 0.9237 Epoch 156/199 128/6993 [..............................] - ETA: 0s - loss: 0.0202 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0880 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0548 - accuracy: 0.9893 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0641 - accuracy: 0.9897 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0773 - accuracy: 0.9866 3328/6993 [=============>................] - ETA: 0s - loss: 0.0705 - accuracy: 0.9871 3968/6993 [================>.............] - ETA: 0s - loss: 0.0659 - accuracy: 0.9871 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0651 - accuracy: 0.9872 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0628 - accuracy: 0.9867 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0592 - accuracy: 0.9874 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0628 - accuracy: 0.9871 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0632 - accuracy: 0.9870 - val_loss: 0.7366 - val_accuracy: 0.9287 Epoch 157/199 128/6993 [..............................] - ETA: 0s - loss: 0.0068 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0489 - accuracy: 0.9870 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0547 - accuracy: 0.9858 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0501 - accuracy: 0.9868 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0759 - accuracy: 0.9866 3328/6993 [=============>................] - ETA: 0s - loss: 0.0700 - accuracy: 0.9862 3968/6993 [================>.............] - ETA: 0s - loss: 0.0727 - accuracy: 0.9861 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0663 - accuracy: 0.9863 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0751 - accuracy: 0.9857 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0782 - accuracy: 0.9844 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0793 - accuracy: 0.9848 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0761 - accuracy: 0.9856 - val_loss: 0.6421 - val_accuracy: 0.9302 Epoch 158/199 128/6993 [..............................] - ETA: 0s - loss: 0.0077 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0654 - accuracy: 0.9933 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1010 - accuracy: 0.9909 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0903 - accuracy: 0.9900 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0807 - accuracy: 0.9901 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0740 - accuracy: 0.9891 4224/6993 [=================>............] - ETA: 0s - loss: 0.0700 - accuracy: 0.9891 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0678 - accuracy: 0.9900 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0650 - accuracy: 0.9897 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0633 - accuracy: 0.9897 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0614 - accuracy: 0.9893 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0622 - accuracy: 0.9891 - val_loss: 0.8462 - val_accuracy: 0.9257 Epoch 159/199 128/6993 [..............................] - ETA: 0s - loss: 0.2716 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0775 - accuracy: 0.9883 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0665 - accuracy: 0.9875 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0748 - accuracy: 0.9875 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1225 - accuracy: 0.9863 3072/6993 [============>.................] - ETA: 0s - loss: 0.1074 - accuracy: 0.9867 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1193 - accuracy: 0.9844 4352/6993 [=================>............] - ETA: 0s - loss: 0.1054 - accuracy: 0.9855 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1075 - accuracy: 0.9852 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0993 - accuracy: 0.9854 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0955 - accuracy: 0.9864 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0909 - accuracy: 0.9867 - val_loss: 0.6072 - val_accuracy: 0.9262 Epoch 160/199 128/6993 [..............................] - ETA: 0s - loss: 0.0232 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0500 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0426 - accuracy: 0.9872 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0370 - accuracy: 0.9896 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0344 - accuracy: 0.9905 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0347 - accuracy: 0.9901 3456/6993 [=============>................] - ETA: 0s - loss: 0.0323 - accuracy: 0.9910 4096/6993 [================>.............] - ETA: 0s - loss: 0.0347 - accuracy: 0.9910 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0466 - accuracy: 0.9903 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0447 - accuracy: 0.9905 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0470 - accuracy: 0.9899 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0493 - accuracy: 0.9895 6993/6993 [==============================] - 1s 103us/sample - loss: 0.0508 - accuracy: 0.9893 - val_loss: 0.6789 - val_accuracy: 0.9292 Epoch 161/199 128/6993 [..............................] - ETA: 0s - loss: 0.0380 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0728 - accuracy: 0.9891 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0555 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0464 - accuracy: 0.9911 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0558 - accuracy: 0.9897 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0716 - accuracy: 0.9898 3456/6993 [=============>................] - ETA: 0s - loss: 0.0911 - accuracy: 0.9899 3968/6993 [================>.............] - ETA: 0s - loss: 0.0829 - accuracy: 0.9897 4352/6993 [=================>............] - ETA: 0s - loss: 0.0931 - accuracy: 0.9883 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0869 - accuracy: 0.9885 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0861 - accuracy: 0.9885 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0837 - accuracy: 0.9879 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0803 - accuracy: 0.9883 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0841 - accuracy: 0.9883 6993/6993 [==============================] - 1s 132us/sample - loss: 0.0812 - accuracy: 0.9886 - val_loss: 0.6422 - val_accuracy: 0.9312 Epoch 162/199 128/6993 [..............................] - ETA: 0s - loss: 0.1028 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0655 - accuracy: 0.9888 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0754 - accuracy: 0.9876 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0708 - accuracy: 0.9867 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0598 - accuracy: 0.9885 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0582 - accuracy: 0.9886 4352/6993 [=================>............] - ETA: 0s - loss: 0.0750 - accuracy: 0.9881 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0687 - accuracy: 0.9889 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0751 - accuracy: 0.9894 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0800 - accuracy: 0.9890 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0854 - accuracy: 0.9884 6993/6993 [==============================] - 1s 99us/sample - loss: 0.0818 - accuracy: 0.9888 - val_loss: 0.6769 - val_accuracy: 0.9323 Epoch 163/199 128/6993 [..............................] - ETA: 0s - loss: 0.0375 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1147 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0943 - accuracy: 0.9872 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1741 - accuracy: 0.9844 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1680 - accuracy: 0.9834 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1481 - accuracy: 0.9847 4224/6993 [=================>............] - ETA: 0s - loss: 0.1422 - accuracy: 0.9837 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1274 - accuracy: 0.9844 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1195 - accuracy: 0.9849 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1112 - accuracy: 0.9857 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1098 - accuracy: 0.9859 6993/6993 [==============================] - 1s 96us/sample - loss: 0.1057 - accuracy: 0.9860 - val_loss: 0.6491 - val_accuracy: 0.9292 Epoch 164/199 128/6993 [..............................] - ETA: 0s - loss: 0.0967 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0690 - accuracy: 0.9859 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0703 - accuracy: 0.9861 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0712 - accuracy: 0.9844 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0622 - accuracy: 0.9865 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0684 - accuracy: 0.9848 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0680 - accuracy: 0.9847 3072/6993 [============>.................] - ETA: 0s - loss: 0.0654 - accuracy: 0.9850 3456/6993 [=============>................] - ETA: 0s - loss: 0.0623 - accuracy: 0.9858 3968/6993 [================>.............] - ETA: 0s - loss: 0.0592 - accuracy: 0.9864 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0556 - accuracy: 0.9866 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0570 - accuracy: 0.9862 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0611 - accuracy: 0.9853 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0617 - accuracy: 0.9856 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0612 - accuracy: 0.9852 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0643 - accuracy: 0.9852 6912/6993 [============================>.] - ETA: 0s - loss: 0.0643 - accuracy: 0.9848 6993/6993 [==============================] - 1s 151us/sample - loss: 0.0636 - accuracy: 0.9850 - val_loss: 0.6442 - val_accuracy: 0.9302 Epoch 165/199 128/6993 [..............................] - ETA: 1s - loss: 0.0089 - accuracy: 1.0000 640/6993 [=>............................] - ETA: 0s - loss: 0.0099 - accuracy: 1.0000 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0505 - accuracy: 0.9957 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0514 - accuracy: 0.9934 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0480 - accuracy: 0.9913 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0485 - accuracy: 0.9914 3200/6993 [============>.................] - ETA: 0s - loss: 0.0576 - accuracy: 0.9916 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0551 - accuracy: 0.9906 4224/6993 [=================>............] - ETA: 0s - loss: 0.0541 - accuracy: 0.9908 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0560 - accuracy: 0.9907 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0576 - accuracy: 0.9908 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0616 - accuracy: 0.9898 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0587 - accuracy: 0.9901 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0609 - accuracy: 0.9900 6912/6993 [============================>.] - ETA: 0s - loss: 0.0616 - accuracy: 0.9899 6993/6993 [==============================] - 1s 123us/sample - loss: 0.0621 - accuracy: 0.9898 - val_loss: 0.7405 - val_accuracy: 0.9323 Epoch 166/199 128/6993 [..............................] - ETA: 0s - loss: 0.0679 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0470 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0740 - accuracy: 0.9874 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0939 - accuracy: 0.9883 3072/6993 [============>.................] - ETA: 0s - loss: 0.0854 - accuracy: 0.9889 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1015 - accuracy: 0.9873 4224/6993 [=================>............] - ETA: 0s - loss: 0.0958 - accuracy: 0.9872 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0954 - accuracy: 0.9866 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0891 - accuracy: 0.9870 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0909 - accuracy: 0.9868 6912/6993 [============================>.] - ETA: 0s - loss: 0.0892 - accuracy: 0.9861 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0883 - accuracy: 0.9863 - val_loss: 0.6808 - val_accuracy: 0.9287 Epoch 167/199 128/6993 [..............................] - ETA: 0s - loss: 0.0039 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0395 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0884 - accuracy: 0.9893 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0889 - accuracy: 0.9878 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0720 - accuracy: 0.9896 3328/6993 [=============>................] - ETA: 0s - loss: 0.0686 - accuracy: 0.9895 3968/6993 [================>.............] - ETA: 0s - loss: 0.0600 - accuracy: 0.9904 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0640 - accuracy: 0.9889 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0664 - accuracy: 0.9889 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0720 - accuracy: 0.9885 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0715 - accuracy: 0.9884 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0699 - accuracy: 0.9884 - val_loss: 0.8061 - val_accuracy: 0.9216 Epoch 168/199 128/6993 [..............................] - ETA: 0s - loss: 0.0139 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0349 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0509 - accuracy: 0.9872 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0511 - accuracy: 0.9863 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0514 - accuracy: 0.9870 3328/6993 [=============>................] - ETA: 0s - loss: 0.0530 - accuracy: 0.9868 3968/6993 [================>.............] - ETA: 0s - loss: 0.0506 - accuracy: 0.9877 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0578 - accuracy: 0.9859 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0669 - accuracy: 0.9865 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0685 - accuracy: 0.9862 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0655 - accuracy: 0.9864 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0663 - accuracy: 0.9860 - val_loss: 0.8260 - val_accuracy: 0.9252 Epoch 169/199 128/6993 [..............................] - ETA: 0s - loss: 0.0560 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0767 - accuracy: 0.9818 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0682 - accuracy: 0.9844 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0622 - accuracy: 0.9878 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0777 - accuracy: 0.9877 3328/6993 [=============>................] - ETA: 0s - loss: 0.0823 - accuracy: 0.9871 3968/6993 [================>.............] - ETA: 0s - loss: 0.0757 - accuracy: 0.9869 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0922 - accuracy: 0.9859 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0874 - accuracy: 0.9859 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0800 - accuracy: 0.9871 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0825 - accuracy: 0.9867 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0906 - accuracy: 0.9858 - val_loss: 0.7459 - val_accuracy: 0.9277 Epoch 170/199 128/6993 [..............................] - ETA: 0s - loss: 0.0739 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.0368 - accuracy: 0.9859 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0781 - accuracy: 0.9861 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1137 - accuracy: 0.9866 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1176 - accuracy: 0.9860 3072/6993 [============>.................] - ETA: 0s - loss: 0.1017 - accuracy: 0.9867 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0929 - accuracy: 0.9868 4352/6993 [=================>............] - ETA: 0s - loss: 0.0907 - accuracy: 0.9864 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0893 - accuracy: 0.9864 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0905 - accuracy: 0.9862 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0978 - accuracy: 0.9862 6784/6993 [============================>.] - ETA: 0s - loss: 0.0980 - accuracy: 0.9860 6993/6993 [==============================] - 1s 102us/sample - loss: 0.1020 - accuracy: 0.9857 - val_loss: 0.7602 - val_accuracy: 0.9267 Epoch 171/199 128/6993 [..............................] - ETA: 0s - loss: 0.0361 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0793 - accuracy: 0.9875 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0717 - accuracy: 0.9854 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0667 - accuracy: 0.9870 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0602 - accuracy: 0.9871 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0810 - accuracy: 0.9858 3456/6993 [=============>................] - ETA: 0s - loss: 0.0741 - accuracy: 0.9864 4096/6993 [================>.............] - ETA: 0s - loss: 0.0824 - accuracy: 0.9868 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0758 - accuracy: 0.9869 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0743 - accuracy: 0.9866 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0818 - accuracy: 0.9857 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0774 - accuracy: 0.9862 6993/6993 [==============================] - 1s 104us/sample - loss: 0.0739 - accuracy: 0.9868 - val_loss: 0.7891 - val_accuracy: 0.9338 Epoch 172/199 128/6993 [..............................] - ETA: 0s - loss: 0.0653 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0211 - accuracy: 0.9948 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0197 - accuracy: 0.9950 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0405 - accuracy: 0.9927 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0640 - accuracy: 0.9926 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0600 - accuracy: 0.9925 3456/6993 [=============>................] - ETA: 0s - loss: 0.0795 - accuracy: 0.9899 3968/6993 [================>.............] - ETA: 0s - loss: 0.0782 - accuracy: 0.9884 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0705 - accuracy: 0.9889 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0643 - accuracy: 0.9895 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0636 - accuracy: 0.9893 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0640 - accuracy: 0.9888 6993/6993 [==============================] - 1s 105us/sample - loss: 0.0606 - accuracy: 0.9893 - val_loss: 0.8702 - val_accuracy: 0.9302 Epoch 173/199 128/6993 [..............................] - ETA: 0s - loss: 0.0564 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.1185 - accuracy: 0.9875 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0958 - accuracy: 0.9878 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0956 - accuracy: 0.9868 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1255 - accuracy: 0.9848 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1295 - accuracy: 0.9840 3072/6993 [============>.................] - ETA: 0s - loss: 0.1169 - accuracy: 0.9850 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1202 - accuracy: 0.9852 4096/6993 [================>.............] - ETA: 0s - loss: 0.1087 - accuracy: 0.9858 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1045 - accuracy: 0.9861 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0986 - accuracy: 0.9863 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0917 - accuracy: 0.9867 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0994 - accuracy: 0.9863 6784/6993 [============================>.] - ETA: 0s - loss: 0.1012 - accuracy: 0.9858 6993/6993 [==============================] - 1s 120us/sample - loss: 0.1023 - accuracy: 0.9858 - val_loss: 0.7209 - val_accuracy: 0.9267 Epoch 174/199 128/6993 [..............................] - ETA: 0s - loss: 0.1032 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.0563 - accuracy: 0.9891 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0795 - accuracy: 0.9887 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0700 - accuracy: 0.9892 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0863 - accuracy: 0.9876 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0933 - accuracy: 0.9851 3328/6993 [=============>................] - ETA: 0s - loss: 0.0846 - accuracy: 0.9859 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0759 - accuracy: 0.9875 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0939 - accuracy: 0.9864 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0914 - accuracy: 0.9859 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0984 - accuracy: 0.9856 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0967 - accuracy: 0.9850 6993/6993 [==============================] - 1s 108us/sample - loss: 0.0956 - accuracy: 0.9850 - val_loss: 0.6995 - val_accuracy: 0.9272 Epoch 175/199 128/6993 [..............................] - ETA: 0s - loss: 0.1516 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0949 - accuracy: 0.9818 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1071 - accuracy: 0.9805 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1409 - accuracy: 0.9818 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1202 - accuracy: 0.9839 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1027 - accuracy: 0.9852 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1029 - accuracy: 0.9851 3328/6993 [=============>................] - ETA: 0s - loss: 0.0933 - accuracy: 0.9865 3968/6993 [================>.............] - ETA: 0s - loss: 0.0914 - accuracy: 0.9861 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0876 - accuracy: 0.9859 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0848 - accuracy: 0.9862 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0833 - accuracy: 0.9858 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0858 - accuracy: 0.9857 6784/6993 [============================>.] - ETA: 0s - loss: 0.0890 - accuracy: 0.9853 6993/6993 [==============================] - 1s 119us/sample - loss: 0.0869 - accuracy: 0.9856 - val_loss: 0.6526 - val_accuracy: 0.9307 Epoch 176/199 128/6993 [..............................] - ETA: 0s - loss: 0.0117 - accuracy: 1.0000 640/6993 [=>............................] - ETA: 0s - loss: 0.0457 - accuracy: 0.9937 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0461 - accuracy: 0.9896 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0532 - accuracy: 0.9898 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0684 - accuracy: 0.9876 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0629 - accuracy: 0.9874 3200/6993 [============>.................] - ETA: 0s - loss: 0.0612 - accuracy: 0.9881 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0866 - accuracy: 0.9883 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0870 - accuracy: 0.9868 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0883 - accuracy: 0.9866 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0840 - accuracy: 0.9867 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0784 - accuracy: 0.9873 6784/6993 [============================>.] - ETA: 0s - loss: 0.0778 - accuracy: 0.9873 6993/6993 [==============================] - 1s 111us/sample - loss: 0.0776 - accuracy: 0.9871 - val_loss: 0.7243 - val_accuracy: 0.9267 Epoch 177/199 128/6993 [..............................] - ETA: 0s - loss: 0.0089 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1144 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0981 - accuracy: 0.9830 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1064 - accuracy: 0.9829 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0914 - accuracy: 0.9847 3328/6993 [=============>................] - ETA: 0s - loss: 0.0949 - accuracy: 0.9850 3968/6993 [================>.............] - ETA: 0s - loss: 0.0960 - accuracy: 0.9849 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0875 - accuracy: 0.9859 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0839 - accuracy: 0.9867 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0787 - accuracy: 0.9872 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0810 - accuracy: 0.9865 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0775 - accuracy: 0.9867 6993/6993 [==============================] - 1s 110us/sample - loss: 0.0789 - accuracy: 0.9864 - val_loss: 0.7614 - val_accuracy: 0.9267 Epoch 178/199 128/6993 [..............................] - ETA: 0s - loss: 0.0115 - accuracy: 1.0000 640/6993 [=>............................] - ETA: 0s - loss: 0.0645 - accuracy: 0.9875 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0889 - accuracy: 0.9852 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0694 - accuracy: 0.9868 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0717 - accuracy: 0.9867 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0802 - accuracy: 0.9862 3328/6993 [=============>................] - ETA: 0s - loss: 0.0872 - accuracy: 0.9859 3968/6993 [================>.............] - ETA: 0s - loss: 0.0894 - accuracy: 0.9856 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0911 - accuracy: 0.9848 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0907 - accuracy: 0.9853 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0906 - accuracy: 0.9849 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1061 - accuracy: 0.9853 6784/6993 [============================>.] - ETA: 0s - loss: 0.1046 - accuracy: 0.9848 6993/6993 [==============================] - 1s 126us/sample - loss: 0.1022 - accuracy: 0.9850 - val_loss: 0.6793 - val_accuracy: 0.9277 Epoch 179/199 128/6993 [..............................] - ETA: 0s - loss: 0.0839 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0951 - accuracy: 0.9844 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0607 - accuracy: 0.9883 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0499 - accuracy: 0.9875 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0733 - accuracy: 0.9867 3328/6993 [=============>................] - ETA: 0s - loss: 0.0804 - accuracy: 0.9865 4224/6993 [=================>............] - ETA: 0s - loss: 0.0829 - accuracy: 0.9863 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0779 - accuracy: 0.9866 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0804 - accuracy: 0.9867 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0781 - accuracy: 0.9868 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0742 - accuracy: 0.9873 - val_loss: 0.6228 - val_accuracy: 0.9312 Epoch 180/199 128/6993 [..............................] - ETA: 0s - loss: 0.0031 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1019 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0760 - accuracy: 0.9862 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0882 - accuracy: 0.9844 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0744 - accuracy: 0.9868 3328/6993 [=============>................] - ETA: 0s - loss: 0.0828 - accuracy: 0.9868 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0799 - accuracy: 0.9867 4096/6993 [================>.............] - ETA: 0s - loss: 0.0794 - accuracy: 0.9868 4352/6993 [=================>............] - ETA: 0s - loss: 0.0790 - accuracy: 0.9871 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0803 - accuracy: 0.9869 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0745 - accuracy: 0.9872 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0721 - accuracy: 0.9872 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0738 - accuracy: 0.9869 6784/6993 [============================>.] - ETA: 0s - loss: 0.0722 - accuracy: 0.9870 6993/6993 [==============================] - 1s 128us/sample - loss: 0.0724 - accuracy: 0.9870 - val_loss: 0.7080 - val_accuracy: 0.9302 Epoch 181/199 128/6993 [..............................] - ETA: 0s - loss: 0.0392 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0205 - accuracy: 0.9948 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0629 - accuracy: 0.9908 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0659 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0583 - accuracy: 0.9892 3328/6993 [=============>................] - ETA: 0s - loss: 0.0845 - accuracy: 0.9871 3968/6993 [================>.............] - ETA: 0s - loss: 0.0732 - accuracy: 0.9889 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0709 - accuracy: 0.9896 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0656 - accuracy: 0.9897 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0644 - accuracy: 0.9896 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0654 - accuracy: 0.9891 6912/6993 [============================>.] - ETA: 0s - loss: 0.0611 - accuracy: 0.9897 6993/6993 [==============================] - 1s 99us/sample - loss: 0.0608 - accuracy: 0.9897 - val_loss: 0.7938 - val_accuracy: 0.9282 Epoch 182/199 128/6993 [..............................] - ETA: 0s - loss: 0.0146 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0495 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0668 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0791 - accuracy: 0.9873 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0728 - accuracy: 0.9870 3328/6993 [=============>................] - ETA: 0s - loss: 0.0745 - accuracy: 0.9868 3968/6993 [================>.............] - ETA: 0s - loss: 0.0738 - accuracy: 0.9871 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0672 - accuracy: 0.9878 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0675 - accuracy: 0.9876 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0693 - accuracy: 0.9874 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0702 - accuracy: 0.9875 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0750 - accuracy: 0.9876 - val_loss: 0.8249 - val_accuracy: 0.9277 Epoch 183/199 128/6993 [..............................] - ETA: 0s - loss: 0.0891 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0521 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0495 - accuracy: 0.9915 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0688 - accuracy: 0.9907 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0801 - accuracy: 0.9900 3328/6993 [=============>................] - ETA: 0s - loss: 0.0831 - accuracy: 0.9892 3968/6993 [================>.............] - ETA: 0s - loss: 0.0795 - accuracy: 0.9884 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0807 - accuracy: 0.9884 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0977 - accuracy: 0.9877 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0942 - accuracy: 0.9875 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0970 - accuracy: 0.9869 6784/6993 [============================>.] - ETA: 0s - loss: 0.0954 - accuracy: 0.9869 6993/6993 [==============================] - 1s 99us/sample - loss: 0.0928 - accuracy: 0.9873 - val_loss: 0.8465 - val_accuracy: 0.9232 Epoch 184/199 128/6993 [..............................] - ETA: 0s - loss: 0.0327 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0345 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0348 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0336 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0411 - accuracy: 0.9896 3200/6993 [============>.................] - ETA: 0s - loss: 0.0443 - accuracy: 0.9894 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0509 - accuracy: 0.9896 4352/6993 [=================>............] - ETA: 0s - loss: 0.0843 - accuracy: 0.9883 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0840 - accuracy: 0.9878 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0858 - accuracy: 0.9870 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0884 - accuracy: 0.9866 6912/6993 [============================>.] - ETA: 0s - loss: 0.0904 - accuracy: 0.9854 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0895 - accuracy: 0.9854 - val_loss: 0.6848 - val_accuracy: 0.9277 Epoch 185/199 128/6993 [..............................] - ETA: 0s - loss: 0.0508 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0297 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0501 - accuracy: 0.9865 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0416 - accuracy: 0.9883 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0397 - accuracy: 0.9883 3072/6993 [============>.................] - ETA: 0s - loss: 0.0513 - accuracy: 0.9876 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0506 - accuracy: 0.9874 4096/6993 [================>.............] - ETA: 0s - loss: 0.0734 - accuracy: 0.9875 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0709 - accuracy: 0.9870 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0724 - accuracy: 0.9875 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0715 - accuracy: 0.9875 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0689 - accuracy: 0.9875 6993/6993 [==============================] - 1s 104us/sample - loss: 0.0726 - accuracy: 0.9866 - val_loss: 0.6753 - val_accuracy: 0.9312 Epoch 186/199 128/6993 [..............................] - ETA: 0s - loss: 0.0205 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0261 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0213 - accuracy: 0.9936 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0343 - accuracy: 0.9922 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0594 - accuracy: 0.9911 3328/6993 [=============>................] - ETA: 0s - loss: 0.0619 - accuracy: 0.9919 3968/6993 [================>.............] - ETA: 0s - loss: 0.0644 - accuracy: 0.9902 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0603 - accuracy: 0.9902 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0667 - accuracy: 0.9899 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0620 - accuracy: 0.9898 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0601 - accuracy: 0.9897 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0652 - accuracy: 0.9897 - val_loss: 0.7675 - val_accuracy: 0.9312 Epoch 187/199 128/6993 [..............................] - ETA: 0s - loss: 0.0079 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0862 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0774 - accuracy: 0.9901 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1279 - accuracy: 0.9873 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1470 - accuracy: 0.9885 3328/6993 [=============>................] - ETA: 0s - loss: 0.1356 - accuracy: 0.9865 3968/6993 [================>.............] - ETA: 0s - loss: 0.1346 - accuracy: 0.9844 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1194 - accuracy: 0.9861 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1108 - accuracy: 0.9863 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1098 - accuracy: 0.9862 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1091 - accuracy: 0.9859 6993/6993 [==============================] - 1s 94us/sample - loss: 0.1085 - accuracy: 0.9854 - val_loss: 0.7483 - val_accuracy: 0.9242 Epoch 188/199 128/6993 [..............................] - ETA: 0s - loss: 0.1217 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0460 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0521 - accuracy: 0.9893 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0495 - accuracy: 0.9896 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0535 - accuracy: 0.9881 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0648 - accuracy: 0.9888 3456/6993 [=============>................] - ETA: 0s - loss: 0.0629 - accuracy: 0.9887 3968/6993 [================>.............] - ETA: 0s - loss: 0.0596 - accuracy: 0.9889 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0683 - accuracy: 0.9888 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0689 - accuracy: 0.9892 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0640 - accuracy: 0.9898 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0684 - accuracy: 0.9895 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0683 - accuracy: 0.9890 6993/6993 [==============================] - 1s 109us/sample - loss: 0.0657 - accuracy: 0.9893 - val_loss: 0.7983 - val_accuracy: 0.9292 Epoch 189/199 128/6993 [..............................] - ETA: 0s - loss: 0.1143 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.0613 - accuracy: 0.9891 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0422 - accuracy: 0.9937 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0604 - accuracy: 0.9927 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0513 - accuracy: 0.9934 3072/6993 [============>.................] - ETA: 0s - loss: 0.0534 - accuracy: 0.9928 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0508 - accuracy: 0.9935 4352/6993 [=================>............] - ETA: 0s - loss: 0.0640 - accuracy: 0.9929 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0677 - accuracy: 0.9924 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0671 - accuracy: 0.9918 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0628 - accuracy: 0.9920 6912/6993 [============================>.] - ETA: 0s - loss: 0.0617 - accuracy: 0.9915 6993/6993 [==============================] - 1s 102us/sample - loss: 0.0646 - accuracy: 0.9913 - val_loss: 0.8474 - val_accuracy: 0.9307 Epoch 190/199 128/6993 [..............................] - ETA: 0s - loss: 0.0762 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.0435 - accuracy: 0.9859 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0576 - accuracy: 0.9875 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9859 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0606 - accuracy: 0.9879 3200/6993 [============>.................] - ETA: 0s - loss: 0.0990 - accuracy: 0.9875 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0933 - accuracy: 0.9870 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0972 - accuracy: 0.9873 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0980 - accuracy: 0.9871 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0990 - accuracy: 0.9858 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0991 - accuracy: 0.9860 6912/6993 [============================>.] - ETA: 0s - loss: 0.0934 - accuracy: 0.9863 6993/6993 [==============================] - 1s 102us/sample - loss: 0.0926 - accuracy: 0.9864 - val_loss: 0.8424 - val_accuracy: 0.9353 Epoch 191/199 128/6993 [..............................] - ETA: 0s - loss: 0.1259 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0751 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0709 - accuracy: 0.9865 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0784 - accuracy: 0.9870 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0681 - accuracy: 0.9868 3072/6993 [============>.................] - ETA: 0s - loss: 0.0743 - accuracy: 0.9863 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0687 - accuracy: 0.9871 4352/6993 [=================>............] - ETA: 0s - loss: 0.0704 - accuracy: 0.9871 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0648 - accuracy: 0.9878 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0848 - accuracy: 0.9875 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0891 - accuracy: 0.9870 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1054 - accuracy: 0.9858 6993/6993 [==============================] - 1s 107us/sample - loss: 0.1114 - accuracy: 0.9853 - val_loss: 0.6624 - val_accuracy: 0.9277 Epoch 192/199 128/6993 [..............................] - ETA: 0s - loss: 0.1375 - accuracy: 0.9609 768/6993 [==>...........................] - ETA: 0s - loss: 0.0566 - accuracy: 0.9792 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0440 - accuracy: 0.9844 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0522 - accuracy: 0.9865 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0758 - accuracy: 0.9827 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0706 - accuracy: 0.9834 3456/6993 [=============>................] - ETA: 0s - loss: 0.0720 - accuracy: 0.9829 4096/6993 [================>.............] - ETA: 0s - loss: 0.0877 - accuracy: 0.9829 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0792 - accuracy: 0.9844 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0753 - accuracy: 0.9846 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0717 - accuracy: 0.9851 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0685 - accuracy: 0.9857 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0655 - accuracy: 0.9862 6912/6993 [============================>.] - ETA: 0s - loss: 0.0657 - accuracy: 0.9861 6993/6993 [==============================] - 1s 123us/sample - loss: 0.0650 - accuracy: 0.9863 - val_loss: 0.8670 - val_accuracy: 0.9237 Epoch 193/199 128/6993 [..............................] - ETA: 0s - loss: 0.0464 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.0716 - accuracy: 0.9844 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0881 - accuracy: 0.9878 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0786 - accuracy: 0.9876 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0798 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0812 - accuracy: 0.9874 3328/6993 [=============>................] - ETA: 0s - loss: 0.0759 - accuracy: 0.9877 3968/6993 [================>.............] - ETA: 0s - loss: 0.0749 - accuracy: 0.9882 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0738 - accuracy: 0.9877 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0721 - accuracy: 0.9876 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0708 - accuracy: 0.9876 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0731 - accuracy: 0.9880 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0726 - accuracy: 0.9878 6912/6993 [============================>.] - ETA: 0s - loss: 0.0839 - accuracy: 0.9871 6993/6993 [==============================] - 1s 124us/sample - loss: 0.0840 - accuracy: 0.9871 - val_loss: 0.8416 - val_accuracy: 0.9232 Epoch 194/199 128/6993 [..............................] - ETA: 0s - loss: 0.0582 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.0352 - accuracy: 0.9891 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0304 - accuracy: 0.9906 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0574 - accuracy: 0.9906 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0518 - accuracy: 0.9902 3200/6993 [============>.................] - ETA: 0s - loss: 0.0637 - accuracy: 0.9897 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0770 - accuracy: 0.9893 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0732 - accuracy: 0.9888 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0659 - accuracy: 0.9896 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0640 - accuracy: 0.9893 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0622 - accuracy: 0.9894 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0648 - accuracy: 0.9890 6993/6993 [==============================] - 1s 109us/sample - loss: 0.0626 - accuracy: 0.9893 - val_loss: 0.9414 - val_accuracy: 0.9252 Epoch 195/199 128/6993 [..............................] - ETA: 0s - loss: 0.0915 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.1470 - accuracy: 0.9859 1152/6993 [===>..........................] - ETA: 0s - loss: 0.1324 - accuracy: 0.9826 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1224 - accuracy: 0.9831 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1123 - accuracy: 0.9833 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1179 - accuracy: 0.9835 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1033 - accuracy: 0.9851 3328/6993 [=============>................] - ETA: 0s - loss: 0.0943 - accuracy: 0.9862 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0960 - accuracy: 0.9859 4352/6993 [=================>............] - ETA: 0s - loss: 0.0890 - accuracy: 0.9867 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0890 - accuracy: 0.9868 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0881 - accuracy: 0.9866 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0826 - accuracy: 0.9874 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0796 - accuracy: 0.9881 6993/6993 [==============================] - 1s 121us/sample - loss: 0.0800 - accuracy: 0.9873 - val_loss: 0.8382 - val_accuracy: 0.9257 Epoch 196/199 128/6993 [..............................] - ETA: 0s - loss: 0.0204 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0439 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0456 - accuracy: 0.9879 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0711 - accuracy: 0.9893 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0861 - accuracy: 0.9870 3200/6993 [============>.................] - ETA: 0s - loss: 0.0848 - accuracy: 0.9866 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0844 - accuracy: 0.9868 4352/6993 [=================>............] - ETA: 0s - loss: 0.0974 - accuracy: 0.9864 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0951 - accuracy: 0.9864 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0925 - accuracy: 0.9865 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1051 - accuracy: 0.9863 6784/6993 [============================>.] - ETA: 0s - loss: 0.1052 - accuracy: 0.9863 6993/6993 [==============================] - 1s 105us/sample - loss: 0.1024 - accuracy: 0.9867 - val_loss: 0.7258 - val_accuracy: 0.9297 Epoch 197/199 128/6993 [..............................] - ETA: 0s - loss: 0.0167 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0748 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0741 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0785 - accuracy: 0.9878 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0795 - accuracy: 0.9866 3328/6993 [=============>................] - ETA: 0s - loss: 0.0768 - accuracy: 0.9865 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0913 - accuracy: 0.9859 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0842 - accuracy: 0.9859 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0937 - accuracy: 0.9846 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0899 - accuracy: 0.9852 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0914 - accuracy: 0.9855 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0887 - accuracy: 0.9851 - val_loss: 0.7811 - val_accuracy: 0.9287 Epoch 198/199 128/6993 [..............................] - ETA: 0s - loss: 0.2027 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0738 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0671 - accuracy: 0.9879 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0723 - accuracy: 0.9865 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1107 - accuracy: 0.9864 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1023 - accuracy: 0.9868 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1137 - accuracy: 0.9872 4224/6993 [=================>............] - ETA: 0s - loss: 0.1176 - accuracy: 0.9863 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1074 - accuracy: 0.9871 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1077 - accuracy: 0.9869 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1003 - accuracy: 0.9871 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0924 - accuracy: 0.9881 6993/6993 [==============================] - 1s 105us/sample - loss: 0.0883 - accuracy: 0.9881 - val_loss: 0.7890 - val_accuracy: 0.9287 Epoch 199/199 128/6993 [..............................] - ETA: 0s - loss: 0.1573 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0890 - accuracy: 0.9805 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1259 - accuracy: 0.9858 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1003 - accuracy: 0.9878 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0924 - accuracy: 0.9867 3072/6993 [============>.................] - ETA: 0s - loss: 0.0824 - accuracy: 0.9867 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0833 - accuracy: 0.9866 4096/6993 [================>.............] - ETA: 0s - loss: 0.0796 - accuracy: 0.9866 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0730 - accuracy: 0.9876 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0742 - accuracy: 0.9868 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0785 - accuracy: 0.9866 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0750 - accuracy: 0.9867 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0738 - accuracy: 0.9867 6912/6993 [============================>.] - ETA: 0s - loss: 0.0776 - accuracy: 0.9867 6993/6993 [==============================] - 1s 125us/sample - loss: 0.0778 - accuracy: 0.9864 - val_loss: 0.7775 - val_accuracy: 0.9206 Evaluating model for iteration 2... 1019/1019 - 0s - loss: 0.6586 - accuracy: 0.9293 Accuracy for iteration 2 0.92934250831604 Training model for iteration 3... Train on 6993 samples, validate on 1978 samples Epoch 1/199 128/6993 [..............................] - ETA: 21s - loss: 2.3599 - accuracy: 0.0703 1024/6993 [===>..........................] - ETA: 2s - loss: 2.1580 - accuracy: 0.2080 1792/6993 [======>.......................] - ETA: 1s - loss: 2.0371 - accuracy: 0.2472 2432/6993 [=========>....................] - ETA: 1s - loss: 1.9627 - accuracy: 0.2751 3200/6993 [============>.................] - ETA: 0s - loss: 1.9112 - accuracy: 0.2994 3712/6993 [==============>...............] - ETA: 0s - loss: 1.8853 - accuracy: 0.3066 4480/6993 [==================>...........] - ETA: 0s - loss: 1.8286 - accuracy: 0.3275 5120/6993 [====================>.........] - ETA: 0s - loss: 1.7926 - accuracy: 0.3408 5632/6993 [=======================>......] - ETA: 0s - loss: 1.7682 - accuracy: 0.3526 6144/6993 [=========================>....] - ETA: 0s - loss: 1.7362 - accuracy: 0.3675 6784/6993 [============================>.] - ETA: 0s - loss: 1.7098 - accuracy: 0.3785 6993/6993 [==============================] - 1s 214us/sample - loss: 1.6990 - accuracy: 0.3840 - val_loss: 1.2115 - val_accuracy: 0.5799 Epoch 2/199 128/6993 [..............................] - ETA: 0s - loss: 1.4697 - accuracy: 0.5000 896/6993 [==>...........................] - ETA: 0s - loss: 1.3964 - accuracy: 0.5201 1536/6993 [=====>........................] - ETA: 0s - loss: 1.3768 - accuracy: 0.5267 2304/6993 [========>.....................] - ETA: 0s - loss: 1.3659 - accuracy: 0.5174 2944/6993 [===========>..................] - ETA: 0s - loss: 1.3485 - accuracy: 0.5248 3584/6993 [==============>...............] - ETA: 0s - loss: 1.3341 - accuracy: 0.5254 4224/6993 [=================>............] - ETA: 0s - loss: 1.3174 - accuracy: 0.5320 4992/6993 [====================>.........] - ETA: 0s - loss: 1.3160 - accuracy: 0.5369 5760/6993 [=======================>......] - ETA: 0s - loss: 1.2894 - accuracy: 0.5474 6400/6993 [==========================>...] - ETA: 0s - loss: 1.2778 - accuracy: 0.5527 6993/6993 [==============================] - 1s 89us/sample - loss: 1.2664 - accuracy: 0.5577 - val_loss: 0.9504 - val_accuracy: 0.6780 Epoch 3/199 128/6993 [..............................] - ETA: 0s - loss: 1.1019 - accuracy: 0.5625 768/6993 [==>...........................] - ETA: 0s - loss: 1.0863 - accuracy: 0.6289 1664/6993 [======>.......................] - ETA: 0s - loss: 1.0543 - accuracy: 0.6436 2432/6993 [=========>....................] - ETA: 0s - loss: 1.0523 - accuracy: 0.6427 3200/6993 [============>.................] - ETA: 0s - loss: 1.0633 - accuracy: 0.6347 3840/6993 [===============>..............] - ETA: 0s - loss: 1.0677 - accuracy: 0.6349 4608/6993 [==================>...........] - ETA: 0s - loss: 1.0581 - accuracy: 0.6389 5248/6993 [=====================>........] - ETA: 0s - loss: 1.0533 - accuracy: 0.6412 5888/6993 [========================>.....] - ETA: 0s - loss: 1.0443 - accuracy: 0.6450 6656/6993 [===========================>..] - ETA: 0s - loss: 1.0461 - accuracy: 0.6466 6993/6993 [==============================] - 1s 85us/sample - loss: 1.0412 - accuracy: 0.6476 - val_loss: 0.8075 - val_accuracy: 0.7280 Epoch 4/199 128/6993 [..............................] - ETA: 0s - loss: 0.9594 - accuracy: 0.6562 896/6993 [==>...........................] - ETA: 0s - loss: 0.8646 - accuracy: 0.7121 1664/6993 [======>.......................] - ETA: 0s - loss: 0.8624 - accuracy: 0.7163 2304/6993 [========>.....................] - ETA: 0s - loss: 0.8943 - accuracy: 0.7079 3072/6993 [============>.................] - ETA: 0s - loss: 0.9266 - accuracy: 0.6973 3968/6993 [================>.............] - ETA: 0s - loss: 0.9085 - accuracy: 0.7021 4736/6993 [===================>..........] - ETA: 0s - loss: 0.9121 - accuracy: 0.6981 5632/6993 [=======================>......] - ETA: 0s - loss: 0.9135 - accuracy: 0.6985 6400/6993 [==========================>...] - ETA: 0s - loss: 0.9068 - accuracy: 0.7022 6993/6993 [==============================] - 1s 83us/sample - loss: 0.9028 - accuracy: 0.7024 - val_loss: 0.7433 - val_accuracy: 0.7578 Epoch 5/199 128/6993 [..............................] - ETA: 0s - loss: 0.8759 - accuracy: 0.6875 768/6993 [==>...........................] - ETA: 0s - loss: 0.8311 - accuracy: 0.7240 1408/6993 [=====>........................] - ETA: 0s - loss: 0.8513 - accuracy: 0.7251 2176/6993 [========>.....................] - ETA: 0s - loss: 0.8477 - accuracy: 0.7252 2944/6993 [===========>..................] - ETA: 0s - loss: 0.8063 - accuracy: 0.7408 3584/6993 [==============>...............] - ETA: 0s - loss: 0.8157 - accuracy: 0.7386 4224/6993 [=================>............] - ETA: 0s - loss: 0.8146 - accuracy: 0.7398 5120/6993 [====================>.........] - ETA: 0s - loss: 0.8181 - accuracy: 0.7395 5888/6993 [========================>.....] - ETA: 0s - loss: 0.8115 - accuracy: 0.7398 6656/6993 [===========================>..] - ETA: 0s - loss: 0.8093 - accuracy: 0.7389 6993/6993 [==============================] - 1s 87us/sample - loss: 0.8011 - accuracy: 0.7413 - val_loss: 0.6966 - val_accuracy: 0.7781 Epoch 6/199 128/6993 [..............................] - ETA: 0s - loss: 0.7106 - accuracy: 0.7812 768/6993 [==>...........................] - ETA: 0s - loss: 0.6898 - accuracy: 0.7747 1664/6993 [======>.......................] - ETA: 0s - loss: 0.6762 - accuracy: 0.7812 2432/6993 [=========>....................] - ETA: 0s - loss: 0.6805 - accuracy: 0.7792 3200/6993 [============>.................] - ETA: 0s - loss: 0.7133 - accuracy: 0.7738 3840/6993 [===============>..............] - ETA: 0s - loss: 0.7294 - accuracy: 0.7677 4480/6993 [==================>...........] - ETA: 0s - loss: 0.7276 - accuracy: 0.7661 5120/6993 [====================>.........] - ETA: 0s - loss: 0.7232 - accuracy: 0.7668 5504/6993 [======================>.......] - ETA: 0s - loss: 0.7132 - accuracy: 0.7705 6016/6993 [========================>.....] - ETA: 0s - loss: 0.7164 - accuracy: 0.7699 6784/6993 [============================>.] - ETA: 0s - loss: 0.7132 - accuracy: 0.7695 6993/6993 [==============================] - 1s 95us/sample - loss: 0.7155 - accuracy: 0.7693 - val_loss: 0.6807 - val_accuracy: 0.7745 Epoch 7/199 128/6993 [..............................] - ETA: 0s - loss: 0.6866 - accuracy: 0.7734 896/6993 [==>...........................] - ETA: 0s - loss: 0.6192 - accuracy: 0.7902 1792/6993 [======>.......................] - ETA: 0s - loss: 0.6282 - accuracy: 0.7969 2560/6993 [=========>....................] - ETA: 0s - loss: 0.6508 - accuracy: 0.7902 3328/6993 [=============>................] - ETA: 0s - loss: 0.6392 - accuracy: 0.7927 4096/6993 [================>.............] - ETA: 0s - loss: 0.6438 - accuracy: 0.7893 4864/6993 [===================>..........] - ETA: 0s - loss: 0.6342 - accuracy: 0.7942 5632/6993 [=======================>......] - ETA: 0s - loss: 0.6296 - accuracy: 0.7956 6400/6993 [==========================>...] - ETA: 0s - loss: 0.6298 - accuracy: 0.7970 6993/6993 [==============================] - 1s 87us/sample - loss: 0.6363 - accuracy: 0.7941 - val_loss: 0.5564 - val_accuracy: 0.8160 Epoch 8/199 128/6993 [..............................] - ETA: 0s - loss: 0.5291 - accuracy: 0.8125 768/6993 [==>...........................] - ETA: 0s - loss: 0.5572 - accuracy: 0.8021 1408/6993 [=====>........................] - ETA: 0s - loss: 0.5473 - accuracy: 0.8139 2176/6993 [========>.....................] - ETA: 0s - loss: 0.5638 - accuracy: 0.8084 2816/6993 [===========>..................] - ETA: 0s - loss: 0.5607 - accuracy: 0.8118 3584/6993 [==============>...............] - ETA: 0s - loss: 0.5877 - accuracy: 0.8050 4352/6993 [=================>............] - ETA: 0s - loss: 0.5833 - accuracy: 0.8086 5120/6993 [====================>.........] - ETA: 0s - loss: 0.5855 - accuracy: 0.8094 5632/6993 [=======================>......] - ETA: 0s - loss: 0.5917 - accuracy: 0.8072 6272/6993 [=========================>....] - ETA: 0s - loss: 0.5870 - accuracy: 0.8088 6912/6993 [============================>.] - ETA: 0s - loss: 0.5843 - accuracy: 0.8092 6993/6993 [==============================] - 1s 89us/sample - loss: 0.5836 - accuracy: 0.8095 - val_loss: 0.5001 - val_accuracy: 0.8367 Epoch 9/199 128/6993 [..............................] - ETA: 0s - loss: 0.4939 - accuracy: 0.8438 896/6993 [==>...........................] - ETA: 0s - loss: 0.5874 - accuracy: 0.8192 1792/6993 [======>.......................] - ETA: 0s - loss: 0.5353 - accuracy: 0.8298 2688/6993 [==========>...................] - ETA: 0s - loss: 0.5419 - accuracy: 0.8274 3456/6993 [=============>................] - ETA: 0s - loss: 0.5391 - accuracy: 0.8261 4096/6993 [================>.............] - ETA: 0s - loss: 0.5275 - accuracy: 0.8313 4480/6993 [==================>...........] - ETA: 0s - loss: 0.5303 - accuracy: 0.8301 4992/6993 [====================>.........] - ETA: 0s - loss: 0.5252 - accuracy: 0.8311 5376/6993 [======================>.......] - ETA: 0s - loss: 0.5178 - accuracy: 0.8335 5888/6993 [========================>.....] - ETA: 0s - loss: 0.5173 - accuracy: 0.8342 6400/6993 [==========================>...] - ETA: 0s - loss: 0.5223 - accuracy: 0.8331 6784/6993 [============================>.] - ETA: 0s - loss: 0.5173 - accuracy: 0.8334 6993/6993 [==============================] - 1s 105us/sample - loss: 0.5134 - accuracy: 0.8345 - val_loss: 0.5518 - val_accuracy: 0.8236 Epoch 10/199 128/6993 [..............................] - ETA: 0s - loss: 0.5264 - accuracy: 0.8438 768/6993 [==>...........................] - ETA: 0s - loss: 0.4586 - accuracy: 0.8581 1280/6993 [====>.........................] - ETA: 0s - loss: 0.4469 - accuracy: 0.8594 1920/6993 [=======>......................] - ETA: 0s - loss: 0.4476 - accuracy: 0.8630 2816/6993 [===========>..................] - ETA: 0s - loss: 0.4500 - accuracy: 0.8626 3584/6993 [==============>...............] - ETA: 0s - loss: 0.4537 - accuracy: 0.8636 4480/6993 [==================>...........] - ETA: 0s - loss: 0.4461 - accuracy: 0.8647 5376/6993 [======================>.......] - ETA: 0s - loss: 0.4488 - accuracy: 0.8638 6144/6993 [=========================>....] - ETA: 0s - loss: 0.4594 - accuracy: 0.8586 6993/6993 [==============================] - 1s 84us/sample - loss: 0.4667 - accuracy: 0.8566 - val_loss: 0.4843 - val_accuracy: 0.8498 Epoch 11/199 128/6993 [..............................] - ETA: 0s - loss: 0.4666 - accuracy: 0.8750 896/6993 [==>...........................] - ETA: 0s - loss: 0.4186 - accuracy: 0.8694 1536/6993 [=====>........................] - ETA: 0s - loss: 0.4061 - accuracy: 0.8730 2304/6993 [========>.....................] - ETA: 0s - loss: 0.3965 - accuracy: 0.8772 3072/6993 [============>.................] - ETA: 0s - loss: 0.4101 - accuracy: 0.8753 3968/6993 [================>.............] - ETA: 0s - loss: 0.4227 - accuracy: 0.8710 4736/6993 [===================>..........] - ETA: 0s - loss: 0.4298 - accuracy: 0.8691 5632/6993 [=======================>......] - ETA: 0s - loss: 0.4409 - accuracy: 0.8642 6400/6993 [==========================>...] - ETA: 0s - loss: 0.4413 - accuracy: 0.8648 6993/6993 [==============================] - 1s 84us/sample - loss: 0.4373 - accuracy: 0.8654 - val_loss: 0.4414 - val_accuracy: 0.8640 Epoch 12/199 128/6993 [..............................] - ETA: 0s - loss: 0.3853 - accuracy: 0.8750 896/6993 [==>...........................] - ETA: 0s - loss: 0.3614 - accuracy: 0.8884 1792/6993 [======>.......................] - ETA: 0s - loss: 0.3674 - accuracy: 0.8873 2560/6993 [=========>....................] - ETA: 0s - loss: 0.3654 - accuracy: 0.8855 3328/6993 [=============>................] - ETA: 0s - loss: 0.3716 - accuracy: 0.8837 4224/6993 [=================>............] - ETA: 0s - loss: 0.3922 - accuracy: 0.8771 4992/6993 [====================>.........] - ETA: 0s - loss: 0.4028 - accuracy: 0.8762 5888/6993 [========================>.....] - ETA: 0s - loss: 0.4005 - accuracy: 0.8750 6656/6993 [===========================>..] - ETA: 0s - loss: 0.3976 - accuracy: 0.8759 6993/6993 [==============================] - 1s 83us/sample - loss: 0.3952 - accuracy: 0.8764 - val_loss: 0.4548 - val_accuracy: 0.8615 Epoch 13/199 128/6993 [..............................] - ETA: 0s - loss: 0.3809 - accuracy: 0.8828 896/6993 [==>...........................] - ETA: 0s - loss: 0.3914 - accuracy: 0.8828 1792/6993 [======>.......................] - ETA: 0s - loss: 0.3586 - accuracy: 0.8856 2560/6993 [=========>....................] - ETA: 0s - loss: 0.3463 - accuracy: 0.8926 3072/6993 [============>.................] - ETA: 0s - loss: 0.3419 - accuracy: 0.8949 3840/6993 [===============>..............] - ETA: 0s - loss: 0.3643 - accuracy: 0.8880 4608/6993 [==================>...........] - ETA: 0s - loss: 0.3630 - accuracy: 0.8889 5376/6993 [======================>.......] - ETA: 0s - loss: 0.3622 - accuracy: 0.8890 6272/6993 [=========================>....] - ETA: 0s - loss: 0.3686 - accuracy: 0.8871 6912/6993 [============================>.] - ETA: 0s - loss: 0.3667 - accuracy: 0.8882 6993/6993 [==============================] - 1s 89us/sample - loss: 0.3661 - accuracy: 0.8886 - val_loss: 0.4546 - val_accuracy: 0.8660 Epoch 14/199 128/6993 [..............................] - ETA: 0s - loss: 0.2623 - accuracy: 0.9219 768/6993 [==>...........................] - ETA: 0s - loss: 0.3226 - accuracy: 0.8919 1536/6993 [=====>........................] - ETA: 0s - loss: 0.3125 - accuracy: 0.8978 2304/6993 [========>.....................] - ETA: 0s - loss: 0.3285 - accuracy: 0.8967 3200/6993 [============>.................] - ETA: 0s - loss: 0.3408 - accuracy: 0.8981 4096/6993 [================>.............] - ETA: 0s - loss: 0.3496 - accuracy: 0.8962 4864/6993 [===================>..........] - ETA: 0s - loss: 0.3412 - accuracy: 0.8978 5760/6993 [=======================>......] - ETA: 0s - loss: 0.3411 - accuracy: 0.8984 6528/6993 [===========================>..] - ETA: 0s - loss: 0.3441 - accuracy: 0.8971 6993/6993 [==============================] - 1s 82us/sample - loss: 0.3435 - accuracy: 0.8975 - val_loss: 0.4084 - val_accuracy: 0.8746 Epoch 15/199 128/6993 [..............................] - ETA: 0s - loss: 0.2884 - accuracy: 0.9219 896/6993 [==>...........................] - ETA: 0s - loss: 0.2821 - accuracy: 0.9107 1792/6993 [======>.......................] - ETA: 0s - loss: 0.3197 - accuracy: 0.9001 2432/6993 [=========>....................] - ETA: 0s - loss: 0.3194 - accuracy: 0.9005 3200/6993 [============>.................] - ETA: 0s - loss: 0.3303 - accuracy: 0.8953 3968/6993 [================>.............] - ETA: 0s - loss: 0.3253 - accuracy: 0.8994 4608/6993 [==================>...........] - ETA: 0s - loss: 0.3234 - accuracy: 0.9004 5376/6993 [======================>.......] - ETA: 0s - loss: 0.3186 - accuracy: 0.9035 6016/6993 [========================>.....] - ETA: 0s - loss: 0.3224 - accuracy: 0.9024 6912/6993 [============================>.] - ETA: 0s - loss: 0.3166 - accuracy: 0.9031 6993/6993 [==============================] - 1s 89us/sample - loss: 0.3160 - accuracy: 0.9035 - val_loss: 0.4145 - val_accuracy: 0.8847 Epoch 16/199 128/6993 [..............................] - ETA: 0s - loss: 0.2810 - accuracy: 0.9062 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2840 - accuracy: 0.9248 1792/6993 [======>.......................] - ETA: 0s - loss: 0.2639 - accuracy: 0.9258 2688/6993 [==========>...................] - ETA: 0s - loss: 0.2721 - accuracy: 0.9189 3456/6993 [=============>................] - ETA: 0s - loss: 0.2902 - accuracy: 0.9164 4096/6993 [================>.............] - ETA: 0s - loss: 0.2952 - accuracy: 0.9138 4864/6993 [===================>..........] - ETA: 0s - loss: 0.3016 - accuracy: 0.9118 5632/6993 [=======================>......] - ETA: 0s - loss: 0.3164 - accuracy: 0.9066 6400/6993 [==========================>...] - ETA: 0s - loss: 0.3067 - accuracy: 0.9081 6993/6993 [==============================] - 1s 87us/sample - loss: 0.3031 - accuracy: 0.9083 - val_loss: 0.4464 - val_accuracy: 0.8771 Epoch 17/199 128/6993 [..............................] - ETA: 0s - loss: 0.1294 - accuracy: 0.9531 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2164 - accuracy: 0.9326 1792/6993 [======>.......................] - ETA: 0s - loss: 0.2543 - accuracy: 0.9275 2304/6993 [========>.....................] - ETA: 0s - loss: 0.2597 - accuracy: 0.9258 2944/6993 [===========>..................] - ETA: 0s - loss: 0.2585 - accuracy: 0.9263 3712/6993 [==============>...............] - ETA: 0s - loss: 0.2562 - accuracy: 0.9240 4480/6993 [==================>...........] - ETA: 0s - loss: 0.2538 - accuracy: 0.9268 5376/6993 [======================>.......] - ETA: 0s - loss: 0.2605 - accuracy: 0.9254 6272/6993 [=========================>....] - ETA: 0s - loss: 0.2615 - accuracy: 0.9246 6993/6993 [==============================] - 1s 84us/sample - loss: 0.2656 - accuracy: 0.9235 - val_loss: 0.4290 - val_accuracy: 0.8827 Epoch 18/199 128/6993 [..............................] - ETA: 0s - loss: 0.2167 - accuracy: 0.9375 896/6993 [==>...........................] - ETA: 0s - loss: 0.2895 - accuracy: 0.9051 1664/6993 [======>.......................] - ETA: 0s - loss: 0.2584 - accuracy: 0.9207 2432/6993 [=========>....................] - ETA: 0s - loss: 0.2459 - accuracy: 0.9235 3328/6993 [=============>................] - ETA: 0s - loss: 0.2339 - accuracy: 0.9294 3968/6993 [================>.............] - ETA: 0s - loss: 0.2289 - accuracy: 0.9315 4480/6993 [==================>...........] - ETA: 0s - loss: 0.2345 - accuracy: 0.9297 5120/6993 [====================>.........] - ETA: 0s - loss: 0.2466 - accuracy: 0.9266 5760/6993 [=======================>......] - ETA: 0s - loss: 0.2511 - accuracy: 0.9259 6400/6993 [==========================>...] - ETA: 0s - loss: 0.2593 - accuracy: 0.9242 6912/6993 [============================>.] - ETA: 0s - loss: 0.2606 - accuracy: 0.9230 6993/6993 [==============================] - 1s 101us/sample - loss: 0.2592 - accuracy: 0.9234 - val_loss: 0.3674 - val_accuracy: 0.8964 Epoch 19/199 128/6993 [..............................] - ETA: 0s - loss: 0.2511 - accuracy: 0.9062 768/6993 [==>...........................] - ETA: 0s - loss: 0.2333 - accuracy: 0.9284 1408/6993 [=====>........................] - ETA: 0s - loss: 0.2125 - accuracy: 0.9318 2304/6993 [========>.....................] - ETA: 0s - loss: 0.2384 - accuracy: 0.9293 3072/6993 [============>.................] - ETA: 0s - loss: 0.2477 - accuracy: 0.9297 3968/6993 [================>.............] - ETA: 0s - loss: 0.2467 - accuracy: 0.9294 4736/6993 [===================>..........] - ETA: 0s - loss: 0.2470 - accuracy: 0.9301 5632/6993 [=======================>......] - ETA: 0s - loss: 0.2488 - accuracy: 0.9276 6528/6993 [===========================>..] - ETA: 0s - loss: 0.2576 - accuracy: 0.9259 6993/6993 [==============================] - 1s 82us/sample - loss: 0.2607 - accuracy: 0.9254 - val_loss: 0.4409 - val_accuracy: 0.8832 Epoch 20/199 128/6993 [..............................] - ETA: 0s - loss: 0.2685 - accuracy: 0.9375 1024/6993 [===>..........................] - ETA: 0s - loss: 0.2048 - accuracy: 0.9355 1920/6993 [=======>......................] - ETA: 0s - loss: 0.2190 - accuracy: 0.9323 2688/6993 [==========>...................] - ETA: 0s - loss: 0.2319 - accuracy: 0.9308 3584/6993 [==============>...............] - ETA: 0s - loss: 0.2167 - accuracy: 0.9330 4352/6993 [=================>............] - ETA: 0s - loss: 0.2228 - accuracy: 0.9343 5120/6993 [====================>.........] - ETA: 0s - loss: 0.2316 - accuracy: 0.9324 6016/6993 [========================>.....] - ETA: 0s - loss: 0.2297 - accuracy: 0.9333 6784/6993 [============================>.] - ETA: 0s - loss: 0.2346 - accuracy: 0.9322 6993/6993 [==============================] - 1s 82us/sample - loss: 0.2329 - accuracy: 0.9325 - val_loss: 0.3793 - val_accuracy: 0.9004 Epoch 21/199 128/6993 [..............................] - ETA: 0s - loss: 0.1456 - accuracy: 0.9531 640/6993 [=>............................] - ETA: 0s - loss: 0.1993 - accuracy: 0.9406 1152/6993 [===>..........................] - ETA: 0s - loss: 0.2021 - accuracy: 0.9401 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1991 - accuracy: 0.9431 2560/6993 [=========>....................] - ETA: 0s - loss: 0.2156 - accuracy: 0.9363 3328/6993 [=============>................] - ETA: 0s - loss: 0.2130 - accuracy: 0.9360 4224/6993 [=================>............] - ETA: 0s - loss: 0.2013 - accuracy: 0.9396 5120/6993 [====================>.........] - ETA: 0s - loss: 0.2112 - accuracy: 0.9363 5888/6993 [========================>.....] - ETA: 0s - loss: 0.2157 - accuracy: 0.9350 6784/6993 [============================>.] - ETA: 0s - loss: 0.2181 - accuracy: 0.9341 6993/6993 [==============================] - 1s 86us/sample - loss: 0.2176 - accuracy: 0.9341 - val_loss: 0.4003 - val_accuracy: 0.8948 Epoch 22/199 128/6993 [..............................] - ETA: 0s - loss: 0.2421 - accuracy: 0.9375 896/6993 [==>...........................] - ETA: 0s - loss: 0.1816 - accuracy: 0.9453 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1815 - accuracy: 0.9501 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1816 - accuracy: 0.9453 3328/6993 [=============>................] - ETA: 0s - loss: 0.1955 - accuracy: 0.9408 3968/6993 [================>.............] - ETA: 0s - loss: 0.1991 - accuracy: 0.9410 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1998 - accuracy: 0.9405 5376/6993 [======================>.......] - ETA: 0s - loss: 0.2016 - accuracy: 0.9399 6144/6993 [=========================>....] - ETA: 0s - loss: 0.2053 - accuracy: 0.9391 6993/6993 [==============================] - 1s 84us/sample - loss: 0.2083 - accuracy: 0.9385 - val_loss: 0.4020 - val_accuracy: 0.9009 Epoch 23/199 128/6993 [..............................] - ETA: 0s - loss: 0.1771 - accuracy: 0.9531 896/6993 [==>...........................] - ETA: 0s - loss: 0.1847 - accuracy: 0.9498 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1745 - accuracy: 0.9487 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1795 - accuracy: 0.9465 3456/6993 [=============>................] - ETA: 0s - loss: 0.1832 - accuracy: 0.9439 4096/6993 [================>.............] - ETA: 0s - loss: 0.1768 - accuracy: 0.9460 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1858 - accuracy: 0.9431 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1918 - accuracy: 0.9412 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1941 - accuracy: 0.9407 6912/6993 [============================>.] - ETA: 0s - loss: 0.1985 - accuracy: 0.9391 6993/6993 [==============================] - 1s 89us/sample - loss: 0.1977 - accuracy: 0.9392 - val_loss: 0.3898 - val_accuracy: 0.9075 Epoch 24/199 128/6993 [..............................] - ETA: 0s - loss: 0.1796 - accuracy: 0.9453 640/6993 [=>............................] - ETA: 0s - loss: 0.2151 - accuracy: 0.9438 1152/6993 [===>..........................] - ETA: 0s - loss: 0.1917 - accuracy: 0.9505 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1833 - accuracy: 0.9501 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1782 - accuracy: 0.9505 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1786 - accuracy: 0.9494 3456/6993 [=============>................] - ETA: 0s - loss: 0.1792 - accuracy: 0.9502 3968/6993 [================>.............] - ETA: 0s - loss: 0.1851 - accuracy: 0.9468 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1899 - accuracy: 0.9453 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1949 - accuracy: 0.9442 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1964 - accuracy: 0.9435 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1940 - accuracy: 0.9440 6993/6993 [==============================] - 1s 100us/sample - loss: 0.1932 - accuracy: 0.9439 - val_loss: 0.3563 - val_accuracy: 0.9055 Epoch 25/199 128/6993 [..............................] - ETA: 0s - loss: 0.1479 - accuracy: 0.9453 896/6993 [==>...........................] - ETA: 0s - loss: 0.1865 - accuracy: 0.9431 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1729 - accuracy: 0.9486 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1648 - accuracy: 0.9499 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1670 - accuracy: 0.9506 3328/6993 [=============>................] - ETA: 0s - loss: 0.1698 - accuracy: 0.9501 3968/6993 [================>.............] - ETA: 0s - loss: 0.1724 - accuracy: 0.9483 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1749 - accuracy: 0.9478 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1787 - accuracy: 0.9468 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1751 - accuracy: 0.9479 6912/6993 [============================>.] - ETA: 0s - loss: 0.1739 - accuracy: 0.9479 6993/6993 [==============================] - 1s 94us/sample - loss: 0.1741 - accuracy: 0.9478 - val_loss: 0.4204 - val_accuracy: 0.8974 Epoch 26/199 128/6993 [..............................] - ETA: 0s - loss: 0.1960 - accuracy: 0.9453 896/6993 [==>...........................] - ETA: 0s - loss: 0.1786 - accuracy: 0.9453 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1673 - accuracy: 0.9489 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1639 - accuracy: 0.9535 3200/6993 [============>.................] - ETA: 0s - loss: 0.1715 - accuracy: 0.9516 3968/6993 [================>.............] - ETA: 0s - loss: 0.1616 - accuracy: 0.9541 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1688 - accuracy: 0.9523 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1761 - accuracy: 0.9511 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1763 - accuracy: 0.9510 6784/6993 [============================>.] - ETA: 0s - loss: 0.1775 - accuracy: 0.9502 6993/6993 [==============================] - 1s 87us/sample - loss: 0.1765 - accuracy: 0.9502 - val_loss: 0.3433 - val_accuracy: 0.9060 Epoch 27/199 128/6993 [..............................] - ETA: 0s - loss: 0.2027 - accuracy: 0.9297 640/6993 [=>............................] - ETA: 0s - loss: 0.1413 - accuracy: 0.9500 1152/6993 [===>..........................] - ETA: 0s - loss: 0.1550 - accuracy: 0.9505 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1670 - accuracy: 0.9498 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1650 - accuracy: 0.9523 3072/6993 [============>.................] - ETA: 0s - loss: 0.1656 - accuracy: 0.9538 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1781 - accuracy: 0.9512 4352/6993 [=================>............] - ETA: 0s - loss: 0.1757 - accuracy: 0.9508 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1733 - accuracy: 0.9513 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1695 - accuracy: 0.9513 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1780 - accuracy: 0.9483 6912/6993 [============================>.] - ETA: 0s - loss: 0.1783 - accuracy: 0.9475 6993/6993 [==============================] - 1s 100us/sample - loss: 0.1779 - accuracy: 0.9475 - val_loss: 0.4319 - val_accuracy: 0.8928 Epoch 28/199 128/6993 [..............................] - ETA: 1s - loss: 0.1387 - accuracy: 0.9297 896/6993 [==>...........................] - ETA: 0s - loss: 0.1540 - accuracy: 0.9565 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1415 - accuracy: 0.9598 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1509 - accuracy: 0.9570 3328/6993 [=============>................] - ETA: 0s - loss: 0.1445 - accuracy: 0.9582 3968/6993 [================>.............] - ETA: 0s - loss: 0.1445 - accuracy: 0.9599 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1506 - accuracy: 0.9588 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1518 - accuracy: 0.9572 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1493 - accuracy: 0.9569 6912/6993 [============================>.] - ETA: 0s - loss: 0.1496 - accuracy: 0.9566 6993/6993 [==============================] - 1s 86us/sample - loss: 0.1489 - accuracy: 0.9568 - val_loss: 0.3902 - val_accuracy: 0.9085 Epoch 29/199 128/6993 [..............................] - ETA: 0s - loss: 0.1350 - accuracy: 0.9531 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1466 - accuracy: 0.9580 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1576 - accuracy: 0.9542 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1452 - accuracy: 0.9576 3200/6993 [============>.................] - ETA: 0s - loss: 0.1424 - accuracy: 0.9591 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1476 - accuracy: 0.9573 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1602 - accuracy: 0.9538 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1535 - accuracy: 0.9554 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1600 - accuracy: 0.9547 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1628 - accuracy: 0.9541 - val_loss: 0.4214 - val_accuracy: 0.9019 Epoch 30/199 128/6993 [..............................] - ETA: 0s - loss: 0.0626 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1013 - accuracy: 0.9678 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1159 - accuracy: 0.9654 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1359 - accuracy: 0.9642 3200/6993 [============>.................] - ETA: 0s - loss: 0.1357 - accuracy: 0.9647 4096/6993 [================>.............] - ETA: 0s - loss: 0.1392 - accuracy: 0.9629 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1420 - accuracy: 0.9611 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1458 - accuracy: 0.9595 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1447 - accuracy: 0.9597 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1467 - accuracy: 0.9595 - val_loss: 0.4489 - val_accuracy: 0.8974 Epoch 31/199 128/6993 [..............................] - ETA: 0s - loss: 0.0855 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.1062 - accuracy: 0.9635 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1397 - accuracy: 0.9579 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1332 - accuracy: 0.9564 3328/6993 [=============>................] - ETA: 0s - loss: 0.1361 - accuracy: 0.9561 4096/6993 [================>.............] - ETA: 0s - loss: 0.1369 - accuracy: 0.9558 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1327 - accuracy: 0.9579 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1342 - accuracy: 0.9580 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1347 - accuracy: 0.9579 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1381 - accuracy: 0.9572 - val_loss: 0.4479 - val_accuracy: 0.8999 Epoch 32/199 128/6993 [..............................] - ETA: 0s - loss: 0.1794 - accuracy: 0.9297 896/6993 [==>...........................] - ETA: 0s - loss: 0.1605 - accuracy: 0.9520 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1461 - accuracy: 0.9585 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1299 - accuracy: 0.9629 3328/6993 [=============>................] - ETA: 0s - loss: 0.1376 - accuracy: 0.9609 4224/6993 [=================>............] - ETA: 0s - loss: 0.1377 - accuracy: 0.9619 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1433 - accuracy: 0.9601 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1438 - accuracy: 0.9606 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1492 - accuracy: 0.9594 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1474 - accuracy: 0.9595 - val_loss: 0.4804 - val_accuracy: 0.8989 Epoch 33/199 128/6993 [..............................] - ETA: 0s - loss: 0.0439 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1588 - accuracy: 0.9648 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1457 - accuracy: 0.9648 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1399 - accuracy: 0.9635 3200/6993 [============>.................] - ETA: 0s - loss: 0.1249 - accuracy: 0.9684 4096/6993 [================>.............] - ETA: 0s - loss: 0.1248 - accuracy: 0.9670 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1320 - accuracy: 0.9646 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1287 - accuracy: 0.9648 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1302 - accuracy: 0.9646 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1293 - accuracy: 0.9645 - val_loss: 0.5424 - val_accuracy: 0.8883 Epoch 34/199 128/6993 [..............................] - ETA: 0s - loss: 0.0984 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.1363 - accuracy: 0.9598 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1304 - accuracy: 0.9627 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1124 - accuracy: 0.9660 3328/6993 [=============>................] - ETA: 0s - loss: 0.1188 - accuracy: 0.9648 4224/6993 [=================>............] - ETA: 0s - loss: 0.1290 - accuracy: 0.9633 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1321 - accuracy: 0.9623 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1305 - accuracy: 0.9627 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1342 - accuracy: 0.9621 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1388 - accuracy: 0.9617 - val_loss: 0.4130 - val_accuracy: 0.9115 Epoch 35/199 128/6993 [..............................] - ETA: 0s - loss: 0.0818 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0956 - accuracy: 0.9710 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1236 - accuracy: 0.9654 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1298 - accuracy: 0.9680 3456/6993 [=============>................] - ETA: 0s - loss: 0.1282 - accuracy: 0.9676 4224/6993 [=================>............] - ETA: 0s - loss: 0.1272 - accuracy: 0.9676 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1331 - accuracy: 0.9652 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1335 - accuracy: 0.9646 6784/6993 [============================>.] - ETA: 0s - loss: 0.1318 - accuracy: 0.9651 6993/6993 [==============================] - 1s 80us/sample - loss: 0.1322 - accuracy: 0.9650 - val_loss: 0.4346 - val_accuracy: 0.9110 Epoch 36/199 128/6993 [..............................] - ETA: 0s - loss: 0.2223 - accuracy: 0.9453 896/6993 [==>...........................] - ETA: 0s - loss: 0.1376 - accuracy: 0.9676 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1420 - accuracy: 0.9674 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1441 - accuracy: 0.9651 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1441 - accuracy: 0.9645 3456/6993 [=============>................] - ETA: 0s - loss: 0.1405 - accuracy: 0.9641 4096/6993 [================>.............] - ETA: 0s - loss: 0.1402 - accuracy: 0.9651 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1352 - accuracy: 0.9654 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1371 - accuracy: 0.9645 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1337 - accuracy: 0.9656 6993/6993 [==============================] - 1s 94us/sample - loss: 0.1292 - accuracy: 0.9665 - val_loss: 0.4424 - val_accuracy: 0.9100 Epoch 37/199 128/6993 [..............................] - ETA: 0s - loss: 0.0477 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1066 - accuracy: 0.9697 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1302 - accuracy: 0.9637 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1235 - accuracy: 0.9669 3456/6993 [=============>................] - ETA: 0s - loss: 0.1422 - accuracy: 0.9653 4352/6993 [=================>............] - ETA: 0s - loss: 0.1339 - accuracy: 0.9676 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1365 - accuracy: 0.9658 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1371 - accuracy: 0.9660 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1352 - accuracy: 0.9660 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1359 - accuracy: 0.9655 - val_loss: 0.4145 - val_accuracy: 0.9075 Epoch 38/199 128/6993 [..............................] - ETA: 0s - loss: 0.0493 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0661 - accuracy: 0.9727 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1412 - accuracy: 0.9577 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1305 - accuracy: 0.9614 3200/6993 [============>.................] - ETA: 0s - loss: 0.1301 - accuracy: 0.9634 3968/6993 [================>.............] - ETA: 0s - loss: 0.1268 - accuracy: 0.9650 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1202 - accuracy: 0.9671 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1165 - accuracy: 0.9684 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1121 - accuracy: 0.9697 6993/6993 [==============================] - 1s 84us/sample - loss: 0.1122 - accuracy: 0.9701 - val_loss: 0.4574 - val_accuracy: 0.9080 Epoch 39/199 128/6993 [..............................] - ETA: 0s - loss: 0.1475 - accuracy: 0.9531 896/6993 [==>...........................] - ETA: 0s - loss: 0.1511 - accuracy: 0.9598 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1427 - accuracy: 0.9615 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1293 - accuracy: 0.9631 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1266 - accuracy: 0.9640 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1361 - accuracy: 0.9629 4352/6993 [=================>............] - ETA: 0s - loss: 0.1335 - accuracy: 0.9607 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1310 - accuracy: 0.9598 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1293 - accuracy: 0.9604 6912/6993 [============================>.] - ETA: 0s - loss: 0.1345 - accuracy: 0.9593 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1352 - accuracy: 0.9594 - val_loss: 0.3935 - val_accuracy: 0.9080 Epoch 40/199 128/6993 [..............................] - ETA: 0s - loss: 0.2470 - accuracy: 0.9062 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1206 - accuracy: 0.9639 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1215 - accuracy: 0.9632 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1243 - accuracy: 0.9613 3456/6993 [=============>................] - ETA: 0s - loss: 0.1146 - accuracy: 0.9630 4224/6993 [=================>............] - ETA: 0s - loss: 0.1182 - accuracy: 0.9619 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1133 - accuracy: 0.9648 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1144 - accuracy: 0.9657 6784/6993 [============================>.] - ETA: 0s - loss: 0.1129 - accuracy: 0.9651 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1135 - accuracy: 0.9651 - val_loss: 0.4117 - val_accuracy: 0.9196 Epoch 41/199 128/6993 [..............................] - ETA: 0s - loss: 0.0108 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0933 - accuracy: 0.9648 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0806 - accuracy: 0.9710 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0820 - accuracy: 0.9710 3456/6993 [=============>................] - ETA: 0s - loss: 0.0757 - accuracy: 0.9731 4224/6993 [=================>............] - ETA: 0s - loss: 0.0827 - accuracy: 0.9742 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0900 - accuracy: 0.9725 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0908 - accuracy: 0.9730 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0936 - accuracy: 0.9723 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0949 - accuracy: 0.9717 - val_loss: 0.4468 - val_accuracy: 0.9085 Epoch 42/199 128/6993 [..............................] - ETA: 0s - loss: 0.0229 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.1033 - accuracy: 0.9754 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0943 - accuracy: 0.9736 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0868 - accuracy: 0.9757 3200/6993 [============>.................] - ETA: 0s - loss: 0.0814 - accuracy: 0.9759 4096/6993 [================>.............] - ETA: 0s - loss: 0.0899 - accuracy: 0.9729 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0969 - accuracy: 0.9716 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1082 - accuracy: 0.9705 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1118 - accuracy: 0.9694 6993/6993 [==============================] - 1s 85us/sample - loss: 0.1105 - accuracy: 0.9688 - val_loss: 0.4104 - val_accuracy: 0.9146 Epoch 43/199 128/6993 [..............................] - ETA: 0s - loss: 0.0643 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0703 - accuracy: 0.9766 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0878 - accuracy: 0.9730 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0979 - accuracy: 0.9745 3200/6993 [============>.................] - ETA: 0s - loss: 0.1022 - accuracy: 0.9728 4096/6993 [================>.............] - ETA: 0s - loss: 0.1006 - accuracy: 0.9739 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0999 - accuracy: 0.9733 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1067 - accuracy: 0.9727 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1099 - accuracy: 0.9717 6993/6993 [==============================] - 1s 87us/sample - loss: 0.1072 - accuracy: 0.9724 - val_loss: 0.4097 - val_accuracy: 0.9191 Epoch 44/199 128/6993 [..............................] - ETA: 0s - loss: 0.1264 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.1134 - accuracy: 0.9676 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0977 - accuracy: 0.9707 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1225 - accuracy: 0.9673 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1136 - accuracy: 0.9699 3072/6993 [============>.................] - ETA: 0s - loss: 0.1049 - accuracy: 0.9720 3456/6993 [=============>................] - ETA: 0s - loss: 0.1006 - accuracy: 0.9725 3968/6993 [================>.............] - ETA: 0s - loss: 0.0979 - accuracy: 0.9730 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0989 - accuracy: 0.9732 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1037 - accuracy: 0.9721 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1026 - accuracy: 0.9722 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1080 - accuracy: 0.9704 6993/6993 [==============================] - 1s 110us/sample - loss: 0.1060 - accuracy: 0.9708 - val_loss: 0.4233 - val_accuracy: 0.9105 Epoch 45/199 128/6993 [..............................] - ETA: 0s - loss: 0.0500 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0654 - accuracy: 0.9792 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0862 - accuracy: 0.9787 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0787 - accuracy: 0.9812 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0736 - accuracy: 0.9811 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0708 - accuracy: 0.9817 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0755 - accuracy: 0.9811 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0791 - accuracy: 0.9787 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0805 - accuracy: 0.9777 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0785 - accuracy: 0.9775 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0843 - accuracy: 0.9771 - val_loss: 0.5074 - val_accuracy: 0.9044 Epoch 46/199 128/6993 [..............................] - ETA: 0s - loss: 0.1700 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0851 - accuracy: 0.9766 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0938 - accuracy: 0.9759 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0949 - accuracy: 0.9753 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0917 - accuracy: 0.9755 3456/6993 [=============>................] - ETA: 0s - loss: 0.0936 - accuracy: 0.9763 4224/6993 [=================>............] - ETA: 0s - loss: 0.0955 - accuracy: 0.9756 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1048 - accuracy: 0.9743 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1044 - accuracy: 0.9735 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1032 - accuracy: 0.9738 6784/6993 [============================>.] - ETA: 0s - loss: 0.1038 - accuracy: 0.9732 6993/6993 [==============================] - 1s 92us/sample - loss: 0.1049 - accuracy: 0.9730 - val_loss: 0.4331 - val_accuracy: 0.9151 Epoch 47/199 128/6993 [..............................] - ETA: 0s - loss: 0.0570 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0870 - accuracy: 0.9821 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0802 - accuracy: 0.9815 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0727 - accuracy: 0.9828 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0773 - accuracy: 0.9823 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0786 - accuracy: 0.9826 3200/6993 [============>.................] - ETA: 0s - loss: 0.0915 - accuracy: 0.9791 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0943 - accuracy: 0.9774 4096/6993 [================>.............] - ETA: 0s - loss: 0.0980 - accuracy: 0.9766 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0957 - accuracy: 0.9766 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1012 - accuracy: 0.9755 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0997 - accuracy: 0.9758 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1074 - accuracy: 0.9742 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1060 - accuracy: 0.9743 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1119 - accuracy: 0.9737 6993/6993 [==============================] - 1s 129us/sample - loss: 0.1105 - accuracy: 0.9737 - val_loss: 0.3872 - val_accuracy: 0.9146 Epoch 48/199 128/6993 [..............................] - ETA: 0s - loss: 0.0665 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.0639 - accuracy: 0.9781 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0789 - accuracy: 0.9800 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0766 - accuracy: 0.9790 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0781 - accuracy: 0.9790 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0773 - accuracy: 0.9801 3072/6993 [============>.................] - ETA: 0s - loss: 0.0780 - accuracy: 0.9788 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0793 - accuracy: 0.9777 3968/6993 [================>.............] - ETA: 0s - loss: 0.0834 - accuracy: 0.9768 4352/6993 [=================>............] - ETA: 0s - loss: 0.0839 - accuracy: 0.9768 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0826 - accuracy: 0.9774 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0883 - accuracy: 0.9766 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0896 - accuracy: 0.9764 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0899 - accuracy: 0.9755 6912/6993 [============================>.] - ETA: 0s - loss: 0.0925 - accuracy: 0.9748 6993/6993 [==============================] - 1s 132us/sample - loss: 0.0927 - accuracy: 0.9750 - val_loss: 0.4483 - val_accuracy: 0.9181 Epoch 49/199 128/6993 [..............................] - ETA: 0s - loss: 0.0894 - accuracy: 0.9688 512/6993 [=>............................] - ETA: 0s - loss: 0.0942 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0834 - accuracy: 0.9805 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0803 - accuracy: 0.9805 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0843 - accuracy: 0.9795 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0936 - accuracy: 0.9785 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1008 - accuracy: 0.9732 3328/6993 [=============>................] - ETA: 0s - loss: 0.0920 - accuracy: 0.9754 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0935 - accuracy: 0.9750 4352/6993 [=================>............] - ETA: 0s - loss: 0.1020 - accuracy: 0.9747 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0989 - accuracy: 0.9757 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0961 - accuracy: 0.9764 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0989 - accuracy: 0.9754 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1043 - accuracy: 0.9745 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1072 - accuracy: 0.9742 6784/6993 [============================>.] - ETA: 0s - loss: 0.1068 - accuracy: 0.9741 6993/6993 [==============================] - 1s 144us/sample - loss: 0.1056 - accuracy: 0.9744 - val_loss: 0.3845 - val_accuracy: 0.9257 Epoch 50/199 128/6993 [..............................] - ETA: 1s - loss: 0.1264 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.0753 - accuracy: 0.9797 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0763 - accuracy: 0.9795 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0806 - accuracy: 0.9773 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0961 - accuracy: 0.9754 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0984 - accuracy: 0.9756 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0975 - accuracy: 0.9754 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0948 - accuracy: 0.9755 3200/6993 [============>.................] - ETA: 0s - loss: 0.0955 - accuracy: 0.9756 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1003 - accuracy: 0.9739 4096/6993 [================>.............] - ETA: 0s - loss: 0.1005 - accuracy: 0.9724 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0995 - accuracy: 0.9731 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1000 - accuracy: 0.9734 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0956 - accuracy: 0.9742 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0924 - accuracy: 0.9746 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0940 - accuracy: 0.9741 6784/6993 [============================>.] - ETA: 0s - loss: 0.0935 - accuracy: 0.9739 6993/6993 [==============================] - 1s 170us/sample - loss: 0.0938 - accuracy: 0.9737 - val_loss: 0.4224 - val_accuracy: 0.9156 Epoch 51/199 128/6993 [..............................] - ETA: 2s - loss: 0.0151 - accuracy: 1.0000 256/6993 [>.............................] - ETA: 3s - loss: 0.0486 - accuracy: 0.9844 512/6993 [=>............................] - ETA: 2s - loss: 0.0628 - accuracy: 0.9805 768/6993 [==>...........................] - ETA: 2s - loss: 0.0932 - accuracy: 0.9779 1024/6993 [===>..........................] - ETA: 2s - loss: 0.0875 - accuracy: 0.9795 1280/6993 [====>.........................] - ETA: 1s - loss: 0.0801 - accuracy: 0.9812 1408/6993 [=====>........................] - ETA: 2s - loss: 0.0810 - accuracy: 0.9808 1664/6993 [======>.......................] - ETA: 1s - loss: 0.0845 - accuracy: 0.9814 1920/6993 [=======>......................] - ETA: 1s - loss: 0.0988 - accuracy: 0.9771 2176/6993 [========>.....................] - ETA: 1s - loss: 0.0966 - accuracy: 0.9766 2560/6993 [=========>....................] - ETA: 1s - loss: 0.0971 - accuracy: 0.9762 2944/6993 [===========>..................] - ETA: 1s - loss: 0.0969 - accuracy: 0.9766 3328/6993 [=============>................] - ETA: 1s - loss: 0.1022 - accuracy: 0.9745 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1070 - accuracy: 0.9735 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1073 - accuracy: 0.9727 4096/6993 [================>.............] - ETA: 0s - loss: 0.1085 - accuracy: 0.9727 4352/6993 [=================>............] - ETA: 0s - loss: 0.1043 - accuracy: 0.9738 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1027 - accuracy: 0.9743 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0997 - accuracy: 0.9745 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0980 - accuracy: 0.9748 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0940 - accuracy: 0.9758 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0915 - accuracy: 0.9764 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0936 - accuracy: 0.9764 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0949 - accuracy: 0.9758 6784/6993 [============================>.] - ETA: 0s - loss: 0.0975 - accuracy: 0.9752 6993/6993 [==============================] - 2s 257us/sample - loss: 0.1005 - accuracy: 0.9745 - val_loss: 0.4849 - val_accuracy: 0.9161 Epoch 52/199 128/6993 [..............................] - ETA: 0s - loss: 0.1345 - accuracy: 0.9531 640/6993 [=>............................] - ETA: 0s - loss: 0.0811 - accuracy: 0.9734 1152/6993 [===>..........................] - ETA: 0s - loss: 0.1095 - accuracy: 0.9688 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1093 - accuracy: 0.9706 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1175 - accuracy: 0.9701 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1086 - accuracy: 0.9719 3328/6993 [=============>................] - ETA: 0s - loss: 0.1027 - accuracy: 0.9721 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1011 - accuracy: 0.9714 4224/6993 [=================>............] - ETA: 0s - loss: 0.0992 - accuracy: 0.9716 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0968 - accuracy: 0.9717 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0940 - accuracy: 0.9724 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0905 - accuracy: 0.9734 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0866 - accuracy: 0.9743 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0890 - accuracy: 0.9743 6993/6993 [==============================] - 1s 130us/sample - loss: 0.0858 - accuracy: 0.9753 - val_loss: 0.4199 - val_accuracy: 0.9232 Epoch 53/199 128/6993 [..............................] - ETA: 0s - loss: 0.0895 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.1241 - accuracy: 0.9766 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0993 - accuracy: 0.9780 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1030 - accuracy: 0.9756 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1005 - accuracy: 0.9754 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1078 - accuracy: 0.9749 4352/6993 [=================>............] - ETA: 0s - loss: 0.0995 - accuracy: 0.9763 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0996 - accuracy: 0.9764 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1070 - accuracy: 0.9759 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1063 - accuracy: 0.9746 6993/6993 [==============================] - 1s 90us/sample - loss: 0.1054 - accuracy: 0.9743 - val_loss: 0.3996 - val_accuracy: 0.9196 Epoch 54/199 128/6993 [..............................] - ETA: 0s - loss: 0.0584 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0588 - accuracy: 0.9870 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0539 - accuracy: 0.9844 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0654 - accuracy: 0.9816 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0759 - accuracy: 0.9803 3200/6993 [============>.................] - ETA: 0s - loss: 0.0915 - accuracy: 0.9772 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0927 - accuracy: 0.9768 4352/6993 [=================>............] - ETA: 0s - loss: 0.0943 - accuracy: 0.9775 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0936 - accuracy: 0.9772 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0949 - accuracy: 0.9762 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0918 - accuracy: 0.9762 6912/6993 [============================>.] - ETA: 0s - loss: 0.0947 - accuracy: 0.9754 6993/6993 [==============================] - 1s 99us/sample - loss: 0.0952 - accuracy: 0.9754 - val_loss: 0.4088 - val_accuracy: 0.9161 Epoch 55/199 128/6993 [..............................] - ETA: 0s - loss: 0.0626 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0624 - accuracy: 0.9805 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0843 - accuracy: 0.9801 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0850 - accuracy: 0.9784 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0785 - accuracy: 0.9799 3328/6993 [=============>................] - ETA: 0s - loss: 0.0802 - accuracy: 0.9787 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0825 - accuracy: 0.9786 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0882 - accuracy: 0.9763 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0882 - accuracy: 0.9762 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0906 - accuracy: 0.9767 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0968 - accuracy: 0.9755 6993/6993 [==============================] - 1s 101us/sample - loss: 0.0961 - accuracy: 0.9758 - val_loss: 0.4207 - val_accuracy: 0.9201 Epoch 56/199 128/6993 [..............................] - ETA: 0s - loss: 0.0713 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.1049 - accuracy: 0.9734 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0910 - accuracy: 0.9781 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0876 - accuracy: 0.9797 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0779 - accuracy: 0.9816 3200/6993 [============>.................] - ETA: 0s - loss: 0.0763 - accuracy: 0.9816 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0855 - accuracy: 0.9792 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0860 - accuracy: 0.9781 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0885 - accuracy: 0.9764 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0872 - accuracy: 0.9764 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0877 - accuracy: 0.9759 6912/6993 [============================>.] - ETA: 0s - loss: 0.0851 - accuracy: 0.9766 6993/6993 [==============================] - 1s 101us/sample - loss: 0.0847 - accuracy: 0.9767 - val_loss: 0.3884 - val_accuracy: 0.9262 Epoch 57/199 128/6993 [..............................] - ETA: 0s - loss: 0.0238 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.1291 - accuracy: 0.9750 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1026 - accuracy: 0.9781 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0971 - accuracy: 0.9781 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0930 - accuracy: 0.9777 3200/6993 [============>.................] - ETA: 0s - loss: 0.0812 - accuracy: 0.9803 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0763 - accuracy: 0.9806 4224/6993 [=================>............] - ETA: 0s - loss: 0.0767 - accuracy: 0.9808 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0762 - accuracy: 0.9796 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0745 - accuracy: 0.9798 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0736 - accuracy: 0.9804 6912/6993 [============================>.] - ETA: 0s - loss: 0.0724 - accuracy: 0.9805 6993/6993 [==============================] - 1s 103us/sample - loss: 0.0725 - accuracy: 0.9806 - val_loss: 0.4836 - val_accuracy: 0.9201 Epoch 58/199 128/6993 [..............................] - ETA: 0s - loss: 0.0617 - accuracy: 0.9766 512/6993 [=>............................] - ETA: 0s - loss: 0.0969 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0914 - accuracy: 0.9743 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1128 - accuracy: 0.9727 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1160 - accuracy: 0.9731 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1204 - accuracy: 0.9733 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1227 - accuracy: 0.9728 3456/6993 [=============>................] - ETA: 0s - loss: 0.1132 - accuracy: 0.9742 3968/6993 [================>.............] - ETA: 0s - loss: 0.1114 - accuracy: 0.9740 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1059 - accuracy: 0.9752 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1083 - accuracy: 0.9757 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1046 - accuracy: 0.9766 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1027 - accuracy: 0.9764 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1046 - accuracy: 0.9759 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1007 - accuracy: 0.9761 6993/6993 [==============================] - 1s 137us/sample - loss: 0.0999 - accuracy: 0.9764 - val_loss: 0.4484 - val_accuracy: 0.9176 Epoch 59/199 128/6993 [..............................] - ETA: 0s - loss: 0.0454 - accuracy: 0.9766 512/6993 [=>............................] - ETA: 0s - loss: 0.0359 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0546 - accuracy: 0.9799 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0869 - accuracy: 0.9751 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0761 - accuracy: 0.9797 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0785 - accuracy: 0.9794 3200/6993 [============>.................] - ETA: 0s - loss: 0.0777 - accuracy: 0.9797 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0784 - accuracy: 0.9795 4224/6993 [=================>............] - ETA: 0s - loss: 0.0753 - accuracy: 0.9804 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0870 - accuracy: 0.9797 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0862 - accuracy: 0.9792 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0867 - accuracy: 0.9792 6912/6993 [============================>.] - ETA: 0s - loss: 0.0888 - accuracy: 0.9783 6993/6993 [==============================] - 1s 109us/sample - loss: 0.0879 - accuracy: 0.9785 - val_loss: 0.4218 - val_accuracy: 0.9237 Epoch 60/199 128/6993 [..............................] - ETA: 0s - loss: 0.0970 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0449 - accuracy: 0.9844 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0579 - accuracy: 0.9835 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0557 - accuracy: 0.9837 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0563 - accuracy: 0.9823 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0567 - accuracy: 0.9823 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0547 - accuracy: 0.9834 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0591 - accuracy: 0.9833 4224/6993 [=================>............] - ETA: 0s - loss: 0.0605 - accuracy: 0.9827 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0670 - accuracy: 0.9816 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0669 - accuracy: 0.9820 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0676 - accuracy: 0.9820 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0705 - accuracy: 0.9815 6993/6993 [==============================] - 1s 116us/sample - loss: 0.0692 - accuracy: 0.9817 - val_loss: 0.4585 - val_accuracy: 0.9247 Epoch 61/199 128/6993 [..............................] - ETA: 0s - loss: 0.0824 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0688 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0881 - accuracy: 0.9815 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0769 - accuracy: 0.9823 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0887 - accuracy: 0.9794 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0877 - accuracy: 0.9800 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0919 - accuracy: 0.9798 4352/6993 [=================>............] - ETA: 0s - loss: 0.1006 - accuracy: 0.9798 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0938 - accuracy: 0.9803 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0963 - accuracy: 0.9794 6784/6993 [============================>.] - ETA: 0s - loss: 0.0920 - accuracy: 0.9802 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0920 - accuracy: 0.9798 - val_loss: 0.4706 - val_accuracy: 0.9161 Epoch 62/199 128/6993 [..............................] - ETA: 1s - loss: 0.0534 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0663 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0546 - accuracy: 0.9874 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0616 - accuracy: 0.9848 3072/6993 [============>.................] - ETA: 0s - loss: 0.0608 - accuracy: 0.9827 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0662 - accuracy: 0.9810 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0731 - accuracy: 0.9799 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0736 - accuracy: 0.9792 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0734 - accuracy: 0.9801 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0783 - accuracy: 0.9798 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0803 - accuracy: 0.9797 - val_loss: 0.4479 - val_accuracy: 0.9206 Epoch 63/199 128/6993 [..............................] - ETA: 0s - loss: 0.0743 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0888 - accuracy: 0.9661 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0915 - accuracy: 0.9723 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0881 - accuracy: 0.9750 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0890 - accuracy: 0.9757 3072/6993 [============>.................] - ETA: 0s - loss: 0.0833 - accuracy: 0.9769 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0799 - accuracy: 0.9789 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0866 - accuracy: 0.9776 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0864 - accuracy: 0.9781 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0886 - accuracy: 0.9776 6912/6993 [============================>.] - ETA: 0s - loss: 0.0901 - accuracy: 0.9764 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0903 - accuracy: 0.9764 - val_loss: 0.4780 - val_accuracy: 0.9100 Epoch 64/199 128/6993 [..............................] - ETA: 0s - loss: 0.0568 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0934 - accuracy: 0.9727 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0857 - accuracy: 0.9766 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0836 - accuracy: 0.9793 3456/6993 [=============>................] - ETA: 0s - loss: 0.0794 - accuracy: 0.9806 4096/6993 [================>.............] - ETA: 0s - loss: 0.0797 - accuracy: 0.9810 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0839 - accuracy: 0.9800 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0843 - accuracy: 0.9787 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0825 - accuracy: 0.9784 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0845 - accuracy: 0.9779 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0906 - accuracy: 0.9778 - val_loss: 0.4477 - val_accuracy: 0.9196 Epoch 65/199 128/6993 [..............................] - ETA: 0s - loss: 0.2038 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1516 - accuracy: 0.9736 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1218 - accuracy: 0.9749 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1040 - accuracy: 0.9766 3456/6993 [=============>................] - ETA: 0s - loss: 0.0991 - accuracy: 0.9786 4096/6993 [================>.............] - ETA: 0s - loss: 0.0974 - accuracy: 0.9788 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0947 - accuracy: 0.9797 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0894 - accuracy: 0.9801 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0914 - accuracy: 0.9802 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0901 - accuracy: 0.9800 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0890 - accuracy: 0.9797 - val_loss: 0.4628 - val_accuracy: 0.9201 Epoch 66/199 128/6993 [..............................] - ETA: 0s - loss: 0.0627 - accuracy: 0.9688 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0742 - accuracy: 0.9756 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0820 - accuracy: 0.9782 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0814 - accuracy: 0.9770 3072/6993 [============>.................] - ETA: 0s - loss: 0.0763 - accuracy: 0.9795 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0813 - accuracy: 0.9802 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0805 - accuracy: 0.9806 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0862 - accuracy: 0.9790 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0864 - accuracy: 0.9783 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0944 - accuracy: 0.9777 6784/6993 [============================>.] - ETA: 0s - loss: 0.0959 - accuracy: 0.9772 6993/6993 [==============================] - 1s 104us/sample - loss: 0.0957 - accuracy: 0.9774 - val_loss: 0.3945 - val_accuracy: 0.9277 Epoch 67/199 128/6993 [..............................] - ETA: 0s - loss: 0.0300 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0277 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0472 - accuracy: 0.9879 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0547 - accuracy: 0.9878 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0488 - accuracy: 0.9885 3456/6993 [=============>................] - ETA: 0s - loss: 0.0582 - accuracy: 0.9861 4224/6993 [=================>............] - ETA: 0s - loss: 0.0662 - accuracy: 0.9851 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0637 - accuracy: 0.9854 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0693 - accuracy: 0.9842 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0684 - accuracy: 0.9839 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0667 - accuracy: 0.9840 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0670 - accuracy: 0.9839 6912/6993 [============================>.] - ETA: 0s - loss: 0.0704 - accuracy: 0.9828 6993/6993 [==============================] - 1s 118us/sample - loss: 0.0714 - accuracy: 0.9824 - val_loss: 0.4867 - val_accuracy: 0.9151 Epoch 68/199 128/6993 [..............................] - ETA: 0s - loss: 0.0270 - accuracy: 0.9844 384/6993 [>.............................] - ETA: 1s - loss: 0.1062 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.1288 - accuracy: 0.9714 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0990 - accuracy: 0.9766 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1050 - accuracy: 0.9746 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1077 - accuracy: 0.9727 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1048 - accuracy: 0.9734 3200/6993 [============>.................] - ETA: 0s - loss: 0.0958 - accuracy: 0.9753 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0924 - accuracy: 0.9763 4096/6993 [================>.............] - ETA: 0s - loss: 0.0889 - accuracy: 0.9768 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0858 - accuracy: 0.9780 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0835 - accuracy: 0.9787 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0818 - accuracy: 0.9790 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0848 - accuracy: 0.9791 6912/6993 [============================>.] - ETA: 0s - loss: 0.0840 - accuracy: 0.9790 6993/6993 [==============================] - 1s 122us/sample - loss: 0.0836 - accuracy: 0.9790 - val_loss: 0.4697 - val_accuracy: 0.9191 Epoch 69/199 128/6993 [..............................] - ETA: 0s - loss: 0.0398 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1076 - accuracy: 0.9779 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1159 - accuracy: 0.9759 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1043 - accuracy: 0.9771 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1047 - accuracy: 0.9780 3456/6993 [=============>................] - ETA: 0s - loss: 0.1006 - accuracy: 0.9780 4096/6993 [================>.............] - ETA: 0s - loss: 0.0933 - accuracy: 0.9797 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0875 - accuracy: 0.9809 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0852 - accuracy: 0.9812 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0863 - accuracy: 0.9808 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0846 - accuracy: 0.9810 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0861 - accuracy: 0.9804 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0833 - accuracy: 0.9812 6993/6993 [==============================] - 1s 133us/sample - loss: 0.0823 - accuracy: 0.9813 - val_loss: 0.4604 - val_accuracy: 0.9216 Epoch 70/199 128/6993 [..............................] - ETA: 1s - loss: 0.1108 - accuracy: 0.9844 384/6993 [>.............................] - ETA: 1s - loss: 0.0667 - accuracy: 0.9818 768/6993 [==>...........................] - ETA: 1s - loss: 0.1077 - accuracy: 0.9779 1280/6993 [====>.........................] - ETA: 1s - loss: 0.0997 - accuracy: 0.9789 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0932 - accuracy: 0.9782 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0952 - accuracy: 0.9779 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0849 - accuracy: 0.9794 3200/6993 [============>.................] - ETA: 0s - loss: 0.0889 - accuracy: 0.9809 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0884 - accuracy: 0.9807 3968/6993 [================>.............] - ETA: 0s - loss: 0.0864 - accuracy: 0.9798 4352/6993 [=================>............] - ETA: 0s - loss: 0.0914 - accuracy: 0.9786 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0949 - accuracy: 0.9783 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0955 - accuracy: 0.9779 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0951 - accuracy: 0.9784 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0943 - accuracy: 0.9789 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0932 - accuracy: 0.9791 6784/6993 [============================>.] - ETA: 0s - loss: 0.0904 - accuracy: 0.9795 6993/6993 [==============================] - 1s 163us/sample - loss: 0.0891 - accuracy: 0.9796 - val_loss: 0.4618 - val_accuracy: 0.9232 Epoch 71/199 128/6993 [..............................] - ETA: 0s - loss: 0.0067 - accuracy: 1.0000 384/6993 [>.............................] - ETA: 1s - loss: 0.1156 - accuracy: 0.9948 768/6993 [==>...........................] - ETA: 0s - loss: 0.0906 - accuracy: 0.9870 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0807 - accuracy: 0.9852 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0862 - accuracy: 0.9844 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0839 - accuracy: 0.9839 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0736 - accuracy: 0.9857 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0679 - accuracy: 0.9855 3200/6993 [============>.................] - ETA: 0s - loss: 0.0674 - accuracy: 0.9850 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0700 - accuracy: 0.9833 3968/6993 [================>.............] - ETA: 0s - loss: 0.0734 - accuracy: 0.9826 4352/6993 [=================>............] - ETA: 0s - loss: 0.0729 - accuracy: 0.9825 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0723 - accuracy: 0.9821 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0828 - accuracy: 0.9816 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0803 - accuracy: 0.9816 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0799 - accuracy: 0.9815 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0795 - accuracy: 0.9809 6993/6993 [==============================] - 1s 155us/sample - loss: 0.0786 - accuracy: 0.9808 - val_loss: 0.4869 - val_accuracy: 0.9166 Epoch 72/199 128/6993 [..............................] - ETA: 0s - loss: 0.0433 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.0298 - accuracy: 0.9891 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0545 - accuracy: 0.9887 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0784 - accuracy: 0.9862 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0852 - accuracy: 0.9829 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0908 - accuracy: 0.9811 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0894 - accuracy: 0.9815 3200/6993 [============>.................] - ETA: 0s - loss: 0.0930 - accuracy: 0.9812 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0913 - accuracy: 0.9807 3968/6993 [================>.............] - ETA: 0s - loss: 0.0917 - accuracy: 0.9798 4352/6993 [=================>............] - ETA: 0s - loss: 0.0886 - accuracy: 0.9795 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0853 - accuracy: 0.9799 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0865 - accuracy: 0.9799 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0904 - accuracy: 0.9791 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0890 - accuracy: 0.9792 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0891 - accuracy: 0.9794 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0870 - accuracy: 0.9797 6784/6993 [============================>.] - ETA: 0s - loss: 0.0885 - accuracy: 0.9795 6993/6993 [==============================] - 1s 160us/sample - loss: 0.0896 - accuracy: 0.9796 - val_loss: 0.5168 - val_accuracy: 0.9110 Epoch 73/199 128/6993 [..............................] - ETA: 0s - loss: 0.0628 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.0504 - accuracy: 0.9859 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0582 - accuracy: 0.9844 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0638 - accuracy: 0.9828 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0613 - accuracy: 0.9828 3200/6993 [============>.................] - ETA: 0s - loss: 0.0587 - accuracy: 0.9834 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0654 - accuracy: 0.9833 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0708 - accuracy: 0.9830 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0715 - accuracy: 0.9828 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0699 - accuracy: 0.9827 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0716 - accuracy: 0.9829 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0783 - accuracy: 0.9823 6993/6993 [==============================] - 1s 106us/sample - loss: 0.0772 - accuracy: 0.9823 - val_loss: 0.5285 - val_accuracy: 0.9232 Epoch 74/199 128/6993 [..............................] - ETA: 0s - loss: 0.0162 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0586 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0758 - accuracy: 0.9844 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0709 - accuracy: 0.9849 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0622 - accuracy: 0.9851 3328/6993 [=============>................] - ETA: 0s - loss: 0.0573 - accuracy: 0.9856 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0557 - accuracy: 0.9852 4352/6993 [=================>............] - ETA: 0s - loss: 0.0628 - accuracy: 0.9846 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0671 - accuracy: 0.9840 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0654 - accuracy: 0.9842 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0636 - accuracy: 0.9842 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0664 - accuracy: 0.9825 6993/6993 [==============================] - 1s 106us/sample - loss: 0.0671 - accuracy: 0.9826 - val_loss: 0.4642 - val_accuracy: 0.9272 Epoch 75/199 128/6993 [..............................] - ETA: 0s - loss: 0.0106 - accuracy: 1.0000 640/6993 [=>............................] - ETA: 0s - loss: 0.0587 - accuracy: 0.9844 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0645 - accuracy: 0.9836 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0626 - accuracy: 0.9854 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0646 - accuracy: 0.9844 3200/6993 [============>.................] - ETA: 0s - loss: 0.0687 - accuracy: 0.9819 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0701 - accuracy: 0.9828 4352/6993 [=================>............] - ETA: 0s - loss: 0.0652 - accuracy: 0.9830 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0612 - accuracy: 0.9848 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0636 - accuracy: 0.9839 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0648 - accuracy: 0.9839 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0770 - accuracy: 0.9836 - val_loss: 0.5057 - val_accuracy: 0.9221 Epoch 76/199 128/6993 [..............................] - ETA: 0s - loss: 0.1489 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0971 - accuracy: 0.9821 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1524 - accuracy: 0.9792 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1216 - accuracy: 0.9812 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1098 - accuracy: 0.9820 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0986 - accuracy: 0.9828 4352/6993 [=================>............] - ETA: 0s - loss: 0.0935 - accuracy: 0.9828 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0888 - accuracy: 0.9832 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0886 - accuracy: 0.9830 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0872 - accuracy: 0.9834 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0838 - accuracy: 0.9837 - val_loss: 0.5425 - val_accuracy: 0.9216 Epoch 77/199 128/6993 [..............................] - ETA: 0s - loss: 0.0409 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0727 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0856 - accuracy: 0.9865 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1001 - accuracy: 0.9805 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1008 - accuracy: 0.9805 3200/6993 [============>.................] - ETA: 0s - loss: 0.0982 - accuracy: 0.9797 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0954 - accuracy: 0.9797 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0903 - accuracy: 0.9801 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0877 - accuracy: 0.9805 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0876 - accuracy: 0.9799 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0906 - accuracy: 0.9795 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0977 - accuracy: 0.9778 - val_loss: 0.4168 - val_accuracy: 0.9252 Epoch 78/199 128/6993 [..............................] - ETA: 0s - loss: 0.0431 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0889 - accuracy: 0.9753 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1072 - accuracy: 0.9720 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0835 - accuracy: 0.9784 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0797 - accuracy: 0.9783 3456/6993 [=============>................] - ETA: 0s - loss: 0.0710 - accuracy: 0.9806 4096/6993 [================>.............] - ETA: 0s - loss: 0.0677 - accuracy: 0.9812 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0720 - accuracy: 0.9818 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0803 - accuracy: 0.9808 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0766 - accuracy: 0.9811 6912/6993 [============================>.] - ETA: 0s - loss: 0.0825 - accuracy: 0.9799 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0823 - accuracy: 0.9800 - val_loss: 0.5044 - val_accuracy: 0.9211 Epoch 79/199 128/6993 [..............................] - ETA: 0s - loss: 0.0681 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0533 - accuracy: 0.9896 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0644 - accuracy: 0.9876 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0571 - accuracy: 0.9887 3072/6993 [============>.................] - ETA: 0s - loss: 0.0499 - accuracy: 0.9896 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0513 - accuracy: 0.9891 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0558 - accuracy: 0.9877 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0632 - accuracy: 0.9859 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0649 - accuracy: 0.9859 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0646 - accuracy: 0.9862 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0708 - accuracy: 0.9857 - val_loss: 0.4895 - val_accuracy: 0.9262 Epoch 80/199 128/6993 [..............................] - ETA: 0s - loss: 0.1055 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0906 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0764 - accuracy: 0.9815 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0738 - accuracy: 0.9807 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0814 - accuracy: 0.9803 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0742 - accuracy: 0.9813 3456/6993 [=============>................] - ETA: 0s - loss: 0.0726 - accuracy: 0.9823 3968/6993 [================>.............] - ETA: 0s - loss: 0.0825 - accuracy: 0.9821 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0774 - accuracy: 0.9828 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0779 - accuracy: 0.9816 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0777 - accuracy: 0.9815 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0789 - accuracy: 0.9814 6784/6993 [============================>.] - ETA: 0s - loss: 0.0741 - accuracy: 0.9823 6993/6993 [==============================] - 1s 111us/sample - loss: 0.0740 - accuracy: 0.9820 - val_loss: 0.4883 - val_accuracy: 0.9262 Epoch 81/199 128/6993 [..............................] - ETA: 0s - loss: 0.0281 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.0468 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0688 - accuracy: 0.9822 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0655 - accuracy: 0.9830 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0639 - accuracy: 0.9830 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0551 - accuracy: 0.9841 4224/6993 [=================>............] - ETA: 0s - loss: 0.0525 - accuracy: 0.9851 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0515 - accuracy: 0.9858 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0517 - accuracy: 0.9853 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0526 - accuracy: 0.9849 6912/6993 [============================>.] - ETA: 0s - loss: 0.0572 - accuracy: 0.9845 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0567 - accuracy: 0.9847 - val_loss: 0.5797 - val_accuracy: 0.9226 Epoch 82/199 128/6993 [..............................] - ETA: 0s - loss: 0.0388 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.0653 - accuracy: 0.9828 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0684 - accuracy: 0.9814 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9850 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0781 - accuracy: 0.9855 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0708 - accuracy: 0.9863 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0823 - accuracy: 0.9860 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0895 - accuracy: 0.9851 3328/6993 [=============>................] - ETA: 0s - loss: 0.0877 - accuracy: 0.9838 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0838 - accuracy: 0.9841 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0800 - accuracy: 0.9839 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0769 - accuracy: 0.9840 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0788 - accuracy: 0.9833 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0760 - accuracy: 0.9842 6993/6993 [==============================] - 1s 130us/sample - loss: 0.0719 - accuracy: 0.9848 - val_loss: 0.5492 - val_accuracy: 0.9282 Epoch 83/199 128/6993 [..............................] - ETA: 0s - loss: 0.2092 - accuracy: 0.9609 640/6993 [=>............................] - ETA: 0s - loss: 0.0782 - accuracy: 0.9797 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0959 - accuracy: 0.9748 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0753 - accuracy: 0.9796 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0895 - accuracy: 0.9798 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0870 - accuracy: 0.9808 3456/6993 [=============>................] - ETA: 0s - loss: 0.0829 - accuracy: 0.9818 4224/6993 [=================>............] - ETA: 0s - loss: 0.0819 - accuracy: 0.9815 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0804 - accuracy: 0.9811 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0822 - accuracy: 0.9804 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0809 - accuracy: 0.9806 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0804 - accuracy: 0.9807 - val_loss: 0.5303 - val_accuracy: 0.9201 Epoch 84/199 128/6993 [..............................] - ETA: 0s - loss: 0.1103 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.0903 - accuracy: 0.9719 1152/6993 [===>..........................] - ETA: 0s - loss: 0.1001 - accuracy: 0.9696 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0909 - accuracy: 0.9730 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0790 - accuracy: 0.9771 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0749 - accuracy: 0.9784 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0731 - accuracy: 0.9788 3072/6993 [============>.................] - ETA: 0s - loss: 0.0676 - accuracy: 0.9798 3456/6993 [=============>................] - ETA: 0s - loss: 0.0635 - accuracy: 0.9806 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0635 - accuracy: 0.9815 4224/6993 [=================>............] - ETA: 0s - loss: 0.0619 - accuracy: 0.9818 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0592 - accuracy: 0.9820 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0643 - accuracy: 0.9814 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0761 - accuracy: 0.9805 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0764 - accuracy: 0.9807 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0773 - accuracy: 0.9807 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0768 - accuracy: 0.9808 6784/6993 [============================>.] - ETA: 0s - loss: 0.0748 - accuracy: 0.9811 6993/6993 [==============================] - 1s 158us/sample - loss: 0.0742 - accuracy: 0.9813 - val_loss: 0.5581 - val_accuracy: 0.9206 Epoch 85/199 128/6993 [..............................] - ETA: 0s - loss: 0.1817 - accuracy: 0.9766 512/6993 [=>............................] - ETA: 0s - loss: 0.0704 - accuracy: 0.9863 896/6993 [==>...........................] - ETA: 0s - loss: 0.0651 - accuracy: 0.9877 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0626 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0579 - accuracy: 0.9850 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0583 - accuracy: 0.9844 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0624 - accuracy: 0.9827 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0568 - accuracy: 0.9830 3328/6993 [=============>................] - ETA: 0s - loss: 0.0523 - accuracy: 0.9847 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0507 - accuracy: 0.9849 4096/6993 [================>.............] - ETA: 0s - loss: 0.0475 - accuracy: 0.9856 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0467 - accuracy: 0.9855 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0452 - accuracy: 0.9859 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0462 - accuracy: 0.9853 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0454 - accuracy: 0.9857 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0503 - accuracy: 0.9855 6993/6993 [==============================] - 1s 143us/sample - loss: 0.0567 - accuracy: 0.9848 - val_loss: 0.5875 - val_accuracy: 0.9110 Epoch 86/199 128/6993 [..............................] - ETA: 1s - loss: 0.0152 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0435 - accuracy: 0.9857 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0396 - accuracy: 0.9876 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0456 - accuracy: 0.9862 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0634 - accuracy: 0.9830 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0741 - accuracy: 0.9810 4224/6993 [=================>............] - ETA: 0s - loss: 0.0710 - accuracy: 0.9815 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0715 - accuracy: 0.9815 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0764 - accuracy: 0.9816 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0733 - accuracy: 0.9822 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0703 - accuracy: 0.9827 6912/6993 [============================>.] - ETA: 0s - loss: 0.0714 - accuracy: 0.9825 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0711 - accuracy: 0.9824 - val_loss: 0.4889 - val_accuracy: 0.9232 Epoch 87/199 128/6993 [..............................] - ETA: 0s - loss: 0.0490 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.1055 - accuracy: 0.9844 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0754 - accuracy: 0.9870 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0626 - accuracy: 0.9876 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0691 - accuracy: 0.9868 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0597 - accuracy: 0.9885 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0586 - accuracy: 0.9878 3456/6993 [=============>................] - ETA: 0s - loss: 0.0571 - accuracy: 0.9878 3968/6993 [================>.............] - ETA: 0s - loss: 0.0583 - accuracy: 0.9866 4352/6993 [=================>............] - ETA: 0s - loss: 0.0571 - accuracy: 0.9869 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0594 - accuracy: 0.9861 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0579 - accuracy: 0.9861 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0645 - accuracy: 0.9862 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0656 - accuracy: 0.9864 6784/6993 [============================>.] - ETA: 0s - loss: 0.0692 - accuracy: 0.9864 6993/6993 [==============================] - 1s 130us/sample - loss: 0.0709 - accuracy: 0.9858 - val_loss: 0.5496 - val_accuracy: 0.9252 Epoch 88/199 128/6993 [..............................] - ETA: 0s - loss: 0.0415 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.0614 - accuracy: 0.9828 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0591 - accuracy: 0.9835 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0541 - accuracy: 0.9838 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0598 - accuracy: 0.9835 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0583 - accuracy: 0.9840 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0614 - accuracy: 0.9838 4224/6993 [=================>............] - ETA: 0s - loss: 0.0787 - accuracy: 0.9825 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0775 - accuracy: 0.9822 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0761 - accuracy: 0.9824 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0721 - accuracy: 0.9830 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0706 - accuracy: 0.9828 - val_loss: 0.5532 - val_accuracy: 0.9262 Epoch 89/199 128/6993 [..............................] - ETA: 0s - loss: 0.1627 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.0535 - accuracy: 0.9906 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0461 - accuracy: 0.9905 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0532 - accuracy: 0.9880 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0607 - accuracy: 0.9863 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0661 - accuracy: 0.9848 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0610 - accuracy: 0.9851 3200/6993 [============>.................] - ETA: 0s - loss: 0.0610 - accuracy: 0.9837 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0636 - accuracy: 0.9830 3968/6993 [================>.............] - ETA: 0s - loss: 0.0630 - accuracy: 0.9831 4352/6993 [=================>............] - ETA: 0s - loss: 0.0690 - accuracy: 0.9832 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0703 - accuracy: 0.9835 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0697 - accuracy: 0.9834 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0692 - accuracy: 0.9835 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0719 - accuracy: 0.9832 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0745 - accuracy: 0.9829 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0778 - accuracy: 0.9833 6993/6993 [==============================] - 1s 159us/sample - loss: 0.0762 - accuracy: 0.9837 - val_loss: 0.5009 - val_accuracy: 0.9257 Epoch 90/199 128/6993 [..............................] - ETA: 1s - loss: 0.0283 - accuracy: 0.9922 512/6993 [=>............................] - ETA: 0s - loss: 0.0292 - accuracy: 0.9941 896/6993 [==>...........................] - ETA: 0s - loss: 0.0527 - accuracy: 0.9900 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0678 - accuracy: 0.9861 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0656 - accuracy: 0.9870 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0732 - accuracy: 0.9849 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0715 - accuracy: 0.9848 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0676 - accuracy: 0.9840 3328/6993 [=============>................] - ETA: 0s - loss: 0.0633 - accuracy: 0.9844 3968/6993 [================>.............] - ETA: 0s - loss: 0.0615 - accuracy: 0.9854 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0600 - accuracy: 0.9855 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0582 - accuracy: 0.9862 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0593 - accuracy: 0.9863 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0606 - accuracy: 0.9858 6912/6993 [============================>.] - ETA: 0s - loss: 0.0621 - accuracy: 0.9855 6993/6993 [==============================] - 1s 122us/sample - loss: 0.0616 - accuracy: 0.9857 - val_loss: 0.5250 - val_accuracy: 0.9252 Epoch 91/199 128/6993 [..............................] - ETA: 0s - loss: 0.1347 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0843 - accuracy: 0.9766 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0696 - accuracy: 0.9785 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0754 - accuracy: 0.9793 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0728 - accuracy: 0.9805 3328/6993 [=============>................] - ETA: 0s - loss: 0.0674 - accuracy: 0.9814 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0647 - accuracy: 0.9831 4352/6993 [=================>............] - ETA: 0s - loss: 0.0610 - accuracy: 0.9844 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0660 - accuracy: 0.9842 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0742 - accuracy: 0.9833 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0765 - accuracy: 0.9829 6912/6993 [============================>.] - ETA: 0s - loss: 0.0750 - accuracy: 0.9821 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0749 - accuracy: 0.9821 - val_loss: 0.5197 - val_accuracy: 0.9297 Epoch 92/199 128/6993 [..............................] - ETA: 1s - loss: 0.0606 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0740 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0542 - accuracy: 0.9908 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0513 - accuracy: 0.9902 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0567 - accuracy: 0.9866 3328/6993 [=============>................] - ETA: 0s - loss: 0.0720 - accuracy: 0.9844 3968/6993 [================>.............] - ETA: 0s - loss: 0.0704 - accuracy: 0.9849 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0741 - accuracy: 0.9837 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0775 - accuracy: 0.9832 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0771 - accuracy: 0.9827 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0750 - accuracy: 0.9825 6993/6993 [==============================] - 1s 97us/sample - loss: 0.0742 - accuracy: 0.9824 - val_loss: 0.5520 - val_accuracy: 0.9171 Epoch 93/199 128/6993 [..............................] - ETA: 0s - loss: 0.1026 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.1100 - accuracy: 0.9766 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0790 - accuracy: 0.9787 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9824 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0791 - accuracy: 0.9840 3328/6993 [=============>................] - ETA: 0s - loss: 0.0762 - accuracy: 0.9841 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0809 - accuracy: 0.9833 4352/6993 [=================>............] - ETA: 0s - loss: 0.0792 - accuracy: 0.9825 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0821 - accuracy: 0.9822 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0856 - accuracy: 0.9814 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0813 - accuracy: 0.9824 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0792 - accuracy: 0.9823 6993/6993 [==============================] - 1s 107us/sample - loss: 0.0770 - accuracy: 0.9828 - val_loss: 0.4853 - val_accuracy: 0.9262 Epoch 94/199 128/6993 [..............................] - ETA: 0s - loss: 0.0454 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0941 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0718 - accuracy: 0.9844 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0830 - accuracy: 0.9834 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0927 - accuracy: 0.9825 3456/6993 [=============>................] - ETA: 0s - loss: 0.0859 - accuracy: 0.9844 4096/6993 [================>.............] - ETA: 0s - loss: 0.0920 - accuracy: 0.9824 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0878 - accuracy: 0.9825 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0818 - accuracy: 0.9833 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0887 - accuracy: 0.9827 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0841 - accuracy: 0.9831 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0802 - accuracy: 0.9837 - val_loss: 0.5213 - val_accuracy: 0.9232 Epoch 95/199 128/6993 [..............................] - ETA: 1s - loss: 0.0754 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.1197 - accuracy: 0.9805 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0880 - accuracy: 0.9830 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0757 - accuracy: 0.9829 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0730 - accuracy: 0.9815 3456/6993 [=============>................] - ETA: 0s - loss: 0.0783 - accuracy: 0.9818 4096/6993 [================>.............] - ETA: 0s - loss: 0.0852 - accuracy: 0.9810 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0828 - accuracy: 0.9816 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0814 - accuracy: 0.9815 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0824 - accuracy: 0.9818 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0850 - accuracy: 0.9818 6784/6993 [============================>.] - ETA: 0s - loss: 0.0821 - accuracy: 0.9826 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0807 - accuracy: 0.9827 - val_loss: 0.4745 - val_accuracy: 0.9282 Epoch 96/199 128/6993 [..............................] - ETA: 0s - loss: 0.1448 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0634 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0534 - accuracy: 0.9893 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0589 - accuracy: 0.9893 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0727 - accuracy: 0.9870 3328/6993 [=============>................] - ETA: 0s - loss: 0.0657 - accuracy: 0.9871 3968/6993 [================>.............] - ETA: 0s - loss: 0.0643 - accuracy: 0.9879 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0597 - accuracy: 0.9886 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0576 - accuracy: 0.9888 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0565 - accuracy: 0.9890 6784/6993 [============================>.] - ETA: 0s - loss: 0.0588 - accuracy: 0.9878 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0589 - accuracy: 0.9873 - val_loss: 0.5375 - val_accuracy: 0.9211 Epoch 97/199 128/6993 [..............................] - ETA: 0s - loss: 0.1937 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.1467 - accuracy: 0.9797 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0911 - accuracy: 0.9852 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0682 - accuracy: 0.9880 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0674 - accuracy: 0.9867 3328/6993 [=============>................] - ETA: 0s - loss: 0.0772 - accuracy: 0.9841 3968/6993 [================>.............] - ETA: 0s - loss: 0.0758 - accuracy: 0.9851 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0734 - accuracy: 0.9850 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0765 - accuracy: 0.9846 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0739 - accuracy: 0.9849 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0735 - accuracy: 0.9844 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0728 - accuracy: 0.9841 - val_loss: 0.5182 - val_accuracy: 0.9232 Epoch 98/199 128/6993 [..............................] - ETA: 0s - loss: 0.3024 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.0981 - accuracy: 0.9828 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1078 - accuracy: 0.9828 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0928 - accuracy: 0.9828 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0740 - accuracy: 0.9851 3328/6993 [=============>................] - ETA: 0s - loss: 0.0742 - accuracy: 0.9853 4096/6993 [================>.............] - ETA: 0s - loss: 0.0720 - accuracy: 0.9849 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0728 - accuracy: 0.9840 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0702 - accuracy: 0.9840 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0751 - accuracy: 0.9837 6784/6993 [============================>.] - ETA: 0s - loss: 0.0733 - accuracy: 0.9842 6993/6993 [==============================] - 1s 97us/sample - loss: 0.0715 - accuracy: 0.9846 - val_loss: 0.5684 - val_accuracy: 0.9232 Epoch 99/199 128/6993 [..............................] - ETA: 0s - loss: 0.0256 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0429 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0465 - accuracy: 0.9858 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0448 - accuracy: 0.9865 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0522 - accuracy: 0.9851 3200/6993 [============>.................] - ETA: 0s - loss: 0.0534 - accuracy: 0.9853 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0641 - accuracy: 0.9846 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0687 - accuracy: 0.9846 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0697 - accuracy: 0.9840 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0714 - accuracy: 0.9837 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0711 - accuracy: 0.9838 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0712 - accuracy: 0.9838 - val_loss: 0.4989 - val_accuracy: 0.9277 Epoch 100/199 128/6993 [..............................] - ETA: 0s - loss: 0.0698 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.0724 - accuracy: 0.9810 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0714 - accuracy: 0.9826 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0630 - accuracy: 0.9844 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0615 - accuracy: 0.9847 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0669 - accuracy: 0.9841 4352/6993 [=================>............] - ETA: 0s - loss: 0.0779 - accuracy: 0.9832 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0737 - accuracy: 0.9832 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0719 - accuracy: 0.9830 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0762 - accuracy: 0.9823 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0777 - accuracy: 0.9821 - val_loss: 0.5272 - val_accuracy: 0.9277 Epoch 101/199 128/6993 [..............................] - ETA: 0s - loss: 0.1675 - accuracy: 0.9531 768/6993 [==>...........................] - ETA: 0s - loss: 0.0819 - accuracy: 0.9727 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0651 - accuracy: 0.9794 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0519 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0566 - accuracy: 0.9840 3328/6993 [=============>................] - ETA: 0s - loss: 0.0560 - accuracy: 0.9844 3968/6993 [================>.............] - ETA: 0s - loss: 0.0571 - accuracy: 0.9849 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0556 - accuracy: 0.9853 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0575 - accuracy: 0.9854 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0595 - accuracy: 0.9849 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0612 - accuracy: 0.9849 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0626 - accuracy: 0.9844 6993/6993 [==============================] - 1s 105us/sample - loss: 0.0621 - accuracy: 0.9843 - val_loss: 0.4987 - val_accuracy: 0.9272 Epoch 102/199 128/6993 [..............................] - ETA: 0s - loss: 0.1599 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.1348 - accuracy: 0.9792 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1133 - accuracy: 0.9851 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1003 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0873 - accuracy: 0.9855 3328/6993 [=============>................] - ETA: 0s - loss: 0.0758 - accuracy: 0.9865 3968/6993 [================>.............] - ETA: 0s - loss: 0.0710 - accuracy: 0.9861 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0737 - accuracy: 0.9848 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0701 - accuracy: 0.9857 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0717 - accuracy: 0.9852 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0737 - accuracy: 0.9857 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0745 - accuracy: 0.9854 - val_loss: 0.5169 - val_accuracy: 0.9211 Epoch 103/199 128/6993 [..............................] - ETA: 0s - loss: 0.1445 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0638 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0599 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0601 - accuracy: 0.9888 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0549 - accuracy: 0.9891 3072/6993 [============>.................] - ETA: 0s - loss: 0.0522 - accuracy: 0.9893 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0468 - accuracy: 0.9900 4352/6993 [=================>............] - ETA: 0s - loss: 0.0466 - accuracy: 0.9901 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0433 - accuracy: 0.9908 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0486 - accuracy: 0.9897 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0534 - accuracy: 0.9896 6784/6993 [============================>.] - ETA: 0s - loss: 0.0590 - accuracy: 0.9888 6993/6993 [==============================] - 1s 102us/sample - loss: 0.0596 - accuracy: 0.9884 - val_loss: 0.6140 - val_accuracy: 0.9211 Epoch 104/199 128/6993 [..............................] - ETA: 0s - loss: 0.1795 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0744 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0715 - accuracy: 0.9837 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0651 - accuracy: 0.9849 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0599 - accuracy: 0.9862 3328/6993 [=============>................] - ETA: 0s - loss: 0.0618 - accuracy: 0.9859 3968/6993 [================>.............] - ETA: 0s - loss: 0.0634 - accuracy: 0.9849 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0584 - accuracy: 0.9859 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0548 - accuracy: 0.9866 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0548 - accuracy: 0.9865 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0603 - accuracy: 0.9864 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0600 - accuracy: 0.9866 - val_loss: 0.5700 - val_accuracy: 0.9196 Epoch 105/199 128/6993 [..............................] - ETA: 1s - loss: 0.1092 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0529 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0566 - accuracy: 0.9879 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0759 - accuracy: 0.9854 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0787 - accuracy: 0.9844 3200/6993 [============>.................] - ETA: 0s - loss: 0.0833 - accuracy: 0.9834 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0868 - accuracy: 0.9830 4224/6993 [=================>............] - ETA: 0s - loss: 0.0839 - accuracy: 0.9834 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0834 - accuracy: 0.9829 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0779 - accuracy: 0.9831 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0781 - accuracy: 0.9839 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0733 - accuracy: 0.9845 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0715 - accuracy: 0.9848 - val_loss: 0.5218 - val_accuracy: 0.9257 Epoch 106/199 128/6993 [..............................] - ETA: 0s - loss: 0.0516 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1059 - accuracy: 0.9792 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1160 - accuracy: 0.9787 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1079 - accuracy: 0.9814 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0978 - accuracy: 0.9827 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0902 - accuracy: 0.9833 3200/6993 [============>.................] - ETA: 0s - loss: 0.0824 - accuracy: 0.9844 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0773 - accuracy: 0.9849 3968/6993 [================>.............] - ETA: 0s - loss: 0.0740 - accuracy: 0.9851 4352/6993 [=================>............] - ETA: 0s - loss: 0.0761 - accuracy: 0.9853 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0904 - accuracy: 0.9850 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0948 - accuracy: 0.9842 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0911 - accuracy: 0.9847 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0894 - accuracy: 0.9849 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0840 - accuracy: 0.9857 6993/6993 [==============================] - 1s 130us/sample - loss: 0.0831 - accuracy: 0.9860 - val_loss: 0.5360 - val_accuracy: 0.9237 Epoch 107/199 128/6993 [..............................] - ETA: 0s - loss: 0.0551 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0712 - accuracy: 0.9805 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0619 - accuracy: 0.9830 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0722 - accuracy: 0.9833 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0738 - accuracy: 0.9826 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0823 - accuracy: 0.9807 3072/6993 [============>.................] - ETA: 0s - loss: 0.0766 - accuracy: 0.9818 3456/6993 [=============>................] - ETA: 0s - loss: 0.0738 - accuracy: 0.9826 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0744 - accuracy: 0.9823 4352/6993 [=================>............] - ETA: 0s - loss: 0.0716 - accuracy: 0.9828 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0761 - accuracy: 0.9823 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0755 - accuracy: 0.9820 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0740 - accuracy: 0.9818 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0741 - accuracy: 0.9819 6993/6993 [==============================] - 1s 125us/sample - loss: 0.0717 - accuracy: 0.9823 - val_loss: 0.5207 - val_accuracy: 0.9267 Epoch 108/199 128/6993 [..............................] - ETA: 0s - loss: 0.0192 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0218 - accuracy: 0.9909 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0357 - accuracy: 0.9906 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0349 - accuracy: 0.9916 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0356 - accuracy: 0.9902 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0526 - accuracy: 0.9891 3072/6993 [============>.................] - ETA: 0s - loss: 0.0497 - accuracy: 0.9886 3328/6993 [=============>................] - ETA: 0s - loss: 0.0508 - accuracy: 0.9883 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0477 - accuracy: 0.9887 3968/6993 [================>.............] - ETA: 0s - loss: 0.0605 - accuracy: 0.9889 4224/6993 [=================>............] - ETA: 0s - loss: 0.0620 - accuracy: 0.9884 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0623 - accuracy: 0.9876 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0678 - accuracy: 0.9870 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0681 - accuracy: 0.9865 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0698 - accuracy: 0.9866 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0719 - accuracy: 0.9867 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0712 - accuracy: 0.9866 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0691 - accuracy: 0.9867 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0695 - accuracy: 0.9863 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0693 - accuracy: 0.9864 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0727 - accuracy: 0.9856 6912/6993 [============================>.] - ETA: 0s - loss: 0.0773 - accuracy: 0.9850 6993/6993 [==============================] - 2s 269us/sample - loss: 0.0775 - accuracy: 0.9848 - val_loss: 0.4940 - val_accuracy: 0.9206 Epoch 109/199 128/6993 [..............................] - ETA: 1s - loss: 0.0777 - accuracy: 0.9844 256/6993 [>.............................] - ETA: 1s - loss: 0.0432 - accuracy: 0.9922 512/6993 [=>............................] - ETA: 1s - loss: 0.0282 - accuracy: 0.9961 896/6993 [==>...........................] - ETA: 1s - loss: 0.0419 - accuracy: 0.9900 1152/6993 [===>..........................] - ETA: 1s - loss: 0.0387 - accuracy: 0.9905 1408/6993 [=====>........................] - ETA: 1s - loss: 0.0523 - accuracy: 0.9893 1792/6993 [======>.......................] - ETA: 1s - loss: 0.0463 - accuracy: 0.9894 2048/6993 [=======>......................] - ETA: 1s - loss: 0.0441 - accuracy: 0.9888 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0493 - accuracy: 0.9881 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0618 - accuracy: 0.9883 3200/6993 [============>.................] - ETA: 0s - loss: 0.0586 - accuracy: 0.9887 3456/6993 [=============>................] - ETA: 0s - loss: 0.0603 - accuracy: 0.9884 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0650 - accuracy: 0.9876 3968/6993 [================>.............] - ETA: 0s - loss: 0.0615 - accuracy: 0.9882 4224/6993 [=================>............] - ETA: 0s - loss: 0.0637 - accuracy: 0.9877 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0648 - accuracy: 0.9870 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0630 - accuracy: 0.9870 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0627 - accuracy: 0.9867 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0641 - accuracy: 0.9864 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0742 - accuracy: 0.9852 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0736 - accuracy: 0.9855 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0734 - accuracy: 0.9854 6993/6993 [==============================] - 2s 227us/sample - loss: 0.0730 - accuracy: 0.9853 - val_loss: 0.5366 - val_accuracy: 0.9257 Epoch 110/199 128/6993 [..............................] - ETA: 1s - loss: 0.0548 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0304 - accuracy: 0.9922 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0459 - accuracy: 0.9870 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0489 - accuracy: 0.9855 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0620 - accuracy: 0.9840 3200/6993 [============>.................] - ETA: 0s - loss: 0.0639 - accuracy: 0.9831 4096/6993 [================>.............] - ETA: 0s - loss: 0.0561 - accuracy: 0.9851 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0584 - accuracy: 0.9848 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0625 - accuracy: 0.9842 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0694 - accuracy: 0.9836 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0692 - accuracy: 0.9841 - val_loss: 0.4575 - val_accuracy: 0.9252 Epoch 111/199 128/6993 [..............................] - ETA: 0s - loss: 0.0389 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0386 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0547 - accuracy: 0.9856 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0540 - accuracy: 0.9863 3200/6993 [============>.................] - ETA: 0s - loss: 0.0528 - accuracy: 0.9862 3968/6993 [================>.............] - ETA: 0s - loss: 0.0558 - accuracy: 0.9859 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0589 - accuracy: 0.9852 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0609 - accuracy: 0.9847 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0642 - accuracy: 0.9847 6912/6993 [============================>.] - ETA: 0s - loss: 0.0614 - accuracy: 0.9858 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0611 - accuracy: 0.9858 - val_loss: 0.6021 - val_accuracy: 0.9282 Epoch 112/199 128/6993 [..............................] - ETA: 0s - loss: 0.0069 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0401 - accuracy: 0.9922 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0538 - accuracy: 0.9902 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0558 - accuracy: 0.9903 3072/6993 [============>.................] - ETA: 0s - loss: 0.0603 - accuracy: 0.9889 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0611 - accuracy: 0.9885 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0682 - accuracy: 0.9878 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0760 - accuracy: 0.9869 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0771 - accuracy: 0.9866 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0764 - accuracy: 0.9861 - val_loss: 0.5725 - val_accuracy: 0.9211 Epoch 113/199 128/6993 [..............................] - ETA: 0s - loss: 0.1047 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0438 - accuracy: 0.9941 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0552 - accuracy: 0.9927 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0588 - accuracy: 0.9895 3328/6993 [=============>................] - ETA: 0s - loss: 0.0603 - accuracy: 0.9889 4096/6993 [================>.............] - ETA: 0s - loss: 0.0597 - accuracy: 0.9883 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0707 - accuracy: 0.9862 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0671 - accuracy: 0.9870 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0653 - accuracy: 0.9873 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0680 - accuracy: 0.9871 - val_loss: 0.5554 - val_accuracy: 0.9277 Epoch 114/199 128/6993 [..............................] - ETA: 0s - loss: 0.0411 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0418 - accuracy: 0.9893 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0481 - accuracy: 0.9883 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0670 - accuracy: 0.9871 3456/6993 [=============>................] - ETA: 0s - loss: 0.0607 - accuracy: 0.9870 4224/6993 [=================>............] - ETA: 0s - loss: 0.0686 - accuracy: 0.9856 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0614 - accuracy: 0.9870 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0700 - accuracy: 0.9859 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0707 - accuracy: 0.9856 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0691 - accuracy: 0.9857 - val_loss: 0.5122 - val_accuracy: 0.9232 Epoch 115/199 128/6993 [..............................] - ETA: 0s - loss: 0.0051 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0543 - accuracy: 0.9911 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0535 - accuracy: 0.9916 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0564 - accuracy: 0.9910 3328/6993 [=============>................] - ETA: 0s - loss: 0.0577 - accuracy: 0.9883 4096/6993 [================>.............] - ETA: 0s - loss: 0.0554 - accuracy: 0.9878 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0625 - accuracy: 0.9891 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0645 - accuracy: 0.9885 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0617 - accuracy: 0.9887 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0621 - accuracy: 0.9888 - val_loss: 0.6154 - val_accuracy: 0.9262 Epoch 116/199 128/6993 [..............................] - ETA: 0s - loss: 0.0468 - accuracy: 0.9766 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0372 - accuracy: 0.9912 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0430 - accuracy: 0.9892 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0617 - accuracy: 0.9877 3200/6993 [============>.................] - ETA: 0s - loss: 0.0700 - accuracy: 0.9878 3968/6993 [================>.............] - ETA: 0s - loss: 0.0645 - accuracy: 0.9882 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0661 - accuracy: 0.9879 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0700 - accuracy: 0.9878 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0636 - accuracy: 0.9878 6912/6993 [============================>.] - ETA: 0s - loss: 0.0601 - accuracy: 0.9883 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0601 - accuracy: 0.9883 - val_loss: 0.7040 - val_accuracy: 0.9232 Epoch 117/199 128/6993 [..............................] - ETA: 0s - loss: 0.0276 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0656 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0722 - accuracy: 0.9838 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0664 - accuracy: 0.9852 3328/6993 [=============>................] - ETA: 0s - loss: 0.0619 - accuracy: 0.9853 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0741 - accuracy: 0.9846 4352/6993 [=================>............] - ETA: 0s - loss: 0.0694 - accuracy: 0.9855 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0725 - accuracy: 0.9852 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0772 - accuracy: 0.9849 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0813 - accuracy: 0.9844 6912/6993 [============================>.] - ETA: 0s - loss: 0.0783 - accuracy: 0.9841 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0776 - accuracy: 0.9843 - val_loss: 0.5354 - val_accuracy: 0.9277 Epoch 118/199 128/6993 [..............................] - ETA: 0s - loss: 0.2332 - accuracy: 0.9609 640/6993 [=>............................] - ETA: 0s - loss: 0.0790 - accuracy: 0.9812 1152/6993 [===>..........................] - ETA: 0s - loss: 0.1374 - accuracy: 0.9809 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1020 - accuracy: 0.9838 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0974 - accuracy: 0.9848 3200/6993 [============>.................] - ETA: 0s - loss: 0.0960 - accuracy: 0.9847 3968/6993 [================>.............] - ETA: 0s - loss: 0.0930 - accuracy: 0.9841 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0830 - accuracy: 0.9857 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0807 - accuracy: 0.9853 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0729 - accuracy: 0.9869 6784/6993 [============================>.] - ETA: 0s - loss: 0.0709 - accuracy: 0.9867 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0698 - accuracy: 0.9867 - val_loss: 0.6073 - val_accuracy: 0.9292 Epoch 119/199 128/6993 [..............................] - ETA: 0s - loss: 0.3533 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0664 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0852 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0853 - accuracy: 0.9855 3328/6993 [=============>................] - ETA: 0s - loss: 0.0864 - accuracy: 0.9859 4096/6993 [================>.............] - ETA: 0s - loss: 0.0769 - accuracy: 0.9871 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0680 - accuracy: 0.9882 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0685 - accuracy: 0.9877 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0683 - accuracy: 0.9873 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0668 - accuracy: 0.9872 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0653 - accuracy: 0.9871 - val_loss: 0.6209 - val_accuracy: 0.9257 Epoch 120/199 128/6993 [..............................] - ETA: 0s - loss: 0.0436 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0344 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0408 - accuracy: 0.9879 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0564 - accuracy: 0.9858 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0650 - accuracy: 0.9858 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0738 - accuracy: 0.9852 4224/6993 [=================>............] - ETA: 0s - loss: 0.0709 - accuracy: 0.9860 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0692 - accuracy: 0.9858 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0699 - accuracy: 0.9855 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0726 - accuracy: 0.9854 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0743 - accuracy: 0.9851 6993/6993 [==============================] - 1s 97us/sample - loss: 0.0714 - accuracy: 0.9851 - val_loss: 0.5534 - val_accuracy: 0.9206 Epoch 121/199 128/6993 [..............................] - ETA: 0s - loss: 0.0342 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0532 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0513 - accuracy: 0.9849 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0428 - accuracy: 0.9863 3328/6993 [=============>................] - ETA: 0s - loss: 0.0534 - accuracy: 0.9871 4224/6993 [=================>............] - ETA: 0s - loss: 0.0498 - accuracy: 0.9877 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0568 - accuracy: 0.9862 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0621 - accuracy: 0.9856 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0616 - accuracy: 0.9856 6993/6993 [==============================] - 1s 85us/sample - loss: 0.0623 - accuracy: 0.9848 - val_loss: 0.6240 - val_accuracy: 0.9262 Epoch 122/199 128/6993 [..............................] - ETA: 0s - loss: 0.0064 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0156 - accuracy: 0.9933 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0419 - accuracy: 0.9922 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0431 - accuracy: 0.9887 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0388 - accuracy: 0.9897 3328/6993 [=============>................] - ETA: 0s - loss: 0.0429 - accuracy: 0.9898 3968/6993 [================>.............] - ETA: 0s - loss: 0.0456 - accuracy: 0.9884 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0480 - accuracy: 0.9883 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0508 - accuracy: 0.9869 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0553 - accuracy: 0.9863 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0599 - accuracy: 0.9859 6993/6993 [==============================] - 1s 101us/sample - loss: 0.0578 - accuracy: 0.9866 - val_loss: 0.5749 - val_accuracy: 0.9282 Epoch 123/199 128/6993 [..............................] - ETA: 0s - loss: 0.0311 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0789 - accuracy: 0.9855 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0648 - accuracy: 0.9868 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0616 - accuracy: 0.9868 3328/6993 [=============>................] - ETA: 0s - loss: 0.0527 - accuracy: 0.9889 4096/6993 [================>.............] - ETA: 0s - loss: 0.0526 - accuracy: 0.9888 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0568 - accuracy: 0.9875 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0605 - accuracy: 0.9866 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0658 - accuracy: 0.9864 6912/6993 [============================>.] - ETA: 0s - loss: 0.0663 - accuracy: 0.9863 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0659 - accuracy: 0.9863 - val_loss: 0.6093 - val_accuracy: 0.9257 Epoch 124/199 128/6993 [..............................] - ETA: 0s - loss: 0.0239 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0358 - accuracy: 0.9911 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0466 - accuracy: 0.9889 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0480 - accuracy: 0.9883 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0469 - accuracy: 0.9886 3456/6993 [=============>................] - ETA: 0s - loss: 0.0538 - accuracy: 0.9881 4352/6993 [=================>............] - ETA: 0s - loss: 0.0550 - accuracy: 0.9876 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0580 - accuracy: 0.9873 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0562 - accuracy: 0.9879 6784/6993 [============================>.] - ETA: 0s - loss: 0.0545 - accuracy: 0.9876 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0533 - accuracy: 0.9878 - val_loss: 0.6191 - val_accuracy: 0.9242 Epoch 125/199 128/6993 [..............................] - ETA: 0s - loss: 0.0677 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1441 - accuracy: 0.9855 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1578 - accuracy: 0.9844 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1332 - accuracy: 0.9860 3072/6993 [============>.................] - ETA: 0s - loss: 0.1155 - accuracy: 0.9863 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1023 - accuracy: 0.9863 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0915 - accuracy: 0.9868 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0957 - accuracy: 0.9863 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0923 - accuracy: 0.9862 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0893 - accuracy: 0.9859 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0861 - accuracy: 0.9863 - val_loss: 0.6022 - val_accuracy: 0.9226 Epoch 126/199 128/6993 [..............................] - ETA: 0s - loss: 0.0040 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0328 - accuracy: 0.9935 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0814 - accuracy: 0.9872 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0789 - accuracy: 0.9873 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0849 - accuracy: 0.9862 3328/6993 [=============>................] - ETA: 0s - loss: 0.0783 - accuracy: 0.9868 3968/6993 [================>.............] - ETA: 0s - loss: 0.0744 - accuracy: 0.9882 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0744 - accuracy: 0.9875 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0705 - accuracy: 0.9876 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0707 - accuracy: 0.9870 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0703 - accuracy: 0.9869 6993/6993 [==============================] - 1s 101us/sample - loss: 0.0699 - accuracy: 0.9868 - val_loss: 0.5716 - val_accuracy: 0.9232 Epoch 127/199 128/6993 [..............................] - ETA: 0s - loss: 0.1665 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0730 - accuracy: 0.9855 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0629 - accuracy: 0.9870 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0728 - accuracy: 0.9877 3200/6993 [============>.................] - ETA: 0s - loss: 0.0736 - accuracy: 0.9862 4096/6993 [================>.............] - ETA: 0s - loss: 0.0704 - accuracy: 0.9875 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0682 - accuracy: 0.9875 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0759 - accuracy: 0.9869 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0720 - accuracy: 0.9867 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0689 - accuracy: 0.9871 - val_loss: 0.5596 - val_accuracy: 0.9186 Epoch 128/199 128/6993 [..............................] - ETA: 0s - loss: 0.0037 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0236 - accuracy: 0.9933 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0328 - accuracy: 0.9904 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0446 - accuracy: 0.9906 3072/6993 [============>.................] - ETA: 0s - loss: 0.0479 - accuracy: 0.9896 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0437 - accuracy: 0.9909 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0420 - accuracy: 0.9909 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0410 - accuracy: 0.9909 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0482 - accuracy: 0.9895 6784/6993 [============================>.] - ETA: 0s - loss: 0.0456 - accuracy: 0.9897 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0458 - accuracy: 0.9891 - val_loss: 0.6478 - val_accuracy: 0.9211 Epoch 129/199 128/6993 [..............................] - ETA: 0s - loss: 0.0706 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0749 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0749 - accuracy: 0.9851 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0804 - accuracy: 0.9862 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1048 - accuracy: 0.9861 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0934 - accuracy: 0.9865 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0870 - accuracy: 0.9870 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0830 - accuracy: 0.9870 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0791 - accuracy: 0.9869 6993/6993 [==============================] - 1s 84us/sample - loss: 0.0837 - accuracy: 0.9871 - val_loss: 0.6275 - val_accuracy: 0.9247 Epoch 130/199 128/6993 [..............................] - ETA: 0s - loss: 0.0434 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0831 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0862 - accuracy: 0.9860 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0995 - accuracy: 0.9840 3328/6993 [=============>................] - ETA: 0s - loss: 0.0932 - accuracy: 0.9832 4096/6993 [================>.............] - ETA: 0s - loss: 0.0916 - accuracy: 0.9834 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0860 - accuracy: 0.9846 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0805 - accuracy: 0.9847 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0840 - accuracy: 0.9850 6912/6993 [============================>.] - ETA: 0s - loss: 0.0853 - accuracy: 0.9851 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0867 - accuracy: 0.9851 - val_loss: 0.6201 - val_accuracy: 0.9247 Epoch 131/199 128/6993 [..............................] - ETA: 0s - loss: 0.0880 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0878 - accuracy: 0.9833 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1019 - accuracy: 0.9833 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0970 - accuracy: 0.9848 3200/6993 [============>.................] - ETA: 0s - loss: 0.0899 - accuracy: 0.9841 3968/6993 [================>.............] - ETA: 0s - loss: 0.0842 - accuracy: 0.9836 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0828 - accuracy: 0.9835 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0814 - accuracy: 0.9840 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0864 - accuracy: 0.9836 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0851 - accuracy: 0.9833 - val_loss: 0.5150 - val_accuracy: 0.9302 Epoch 132/199 128/6993 [..............................] - ETA: 0s - loss: 0.0996 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0707 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0591 - accuracy: 0.9886 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0684 - accuracy: 0.9878 3072/6993 [============>.................] - ETA: 0s - loss: 0.0614 - accuracy: 0.9886 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0581 - accuracy: 0.9883 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0565 - accuracy: 0.9872 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0545 - accuracy: 0.9878 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0592 - accuracy: 0.9880 6784/6993 [============================>.] - ETA: 0s - loss: 0.0579 - accuracy: 0.9879 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0574 - accuracy: 0.9878 - val_loss: 0.6342 - val_accuracy: 0.9211 Epoch 133/199 128/6993 [..............................] - ETA: 0s - loss: 0.0093 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0702 - accuracy: 0.9870 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0828 - accuracy: 0.9850 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0779 - accuracy: 0.9875 3328/6993 [=============>................] - ETA: 0s - loss: 0.0910 - accuracy: 0.9853 4096/6993 [================>.............] - ETA: 0s - loss: 0.0820 - accuracy: 0.9866 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0776 - accuracy: 0.9868 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0713 - accuracy: 0.9872 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0714 - accuracy: 0.9862 6993/6993 [==============================] - 1s 82us/sample - loss: 0.0743 - accuracy: 0.9858 - val_loss: 0.5899 - val_accuracy: 0.9221 Epoch 134/199 128/6993 [..............................] - ETA: 0s - loss: 0.0125 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0473 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0419 - accuracy: 0.9883 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0532 - accuracy: 0.9867 3200/6993 [============>.................] - ETA: 0s - loss: 0.0609 - accuracy: 0.9862 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0626 - accuracy: 0.9867 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0559 - accuracy: 0.9875 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0537 - accuracy: 0.9872 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0523 - accuracy: 0.9873 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0556 - accuracy: 0.9870 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0586 - accuracy: 0.9865 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0652 - accuracy: 0.9858 - val_loss: 0.5609 - val_accuracy: 0.9267 Epoch 135/199 128/6993 [..............................] - ETA: 0s - loss: 0.0220 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0501 - accuracy: 0.9866 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0524 - accuracy: 0.9863 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0593 - accuracy: 0.9848 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0561 - accuracy: 0.9858 3456/6993 [=============>................] - ETA: 0s - loss: 0.0520 - accuracy: 0.9870 4096/6993 [================>.............] - ETA: 0s - loss: 0.0509 - accuracy: 0.9875 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0545 - accuracy: 0.9870 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0543 - accuracy: 0.9873 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0647 - accuracy: 0.9864 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0630 - accuracy: 0.9871 - val_loss: 0.6137 - val_accuracy: 0.9307 Epoch 136/199 128/6993 [..............................] - ETA: 0s - loss: 0.3470 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.0813 - accuracy: 0.9866 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0560 - accuracy: 0.9888 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0444 - accuracy: 0.9902 3328/6993 [=============>................] - ETA: 0s - loss: 0.0411 - accuracy: 0.9907 3968/6993 [================>.............] - ETA: 0s - loss: 0.0408 - accuracy: 0.9912 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0397 - accuracy: 0.9908 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0433 - accuracy: 0.9900 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0425 - accuracy: 0.9907 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0470 - accuracy: 0.9898 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0521 - accuracy: 0.9893 - val_loss: 0.5953 - val_accuracy: 0.9277 Epoch 137/199 128/6993 [..............................] - ETA: 1s - loss: 0.0818 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0742 - accuracy: 0.9911 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0880 - accuracy: 0.9874 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1130 - accuracy: 0.9852 3072/6993 [============>.................] - ETA: 0s - loss: 0.1123 - accuracy: 0.9834 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1018 - accuracy: 0.9841 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0975 - accuracy: 0.9846 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0889 - accuracy: 0.9850 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0885 - accuracy: 0.9846 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0890 - accuracy: 0.9849 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0892 - accuracy: 0.9845 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0885 - accuracy: 0.9846 - val_loss: 0.5928 - val_accuracy: 0.9262 Epoch 138/199 128/6993 [..............................] - ETA: 0s - loss: 0.0116 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0539 - accuracy: 0.9893 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0610 - accuracy: 0.9872 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9847 3456/6993 [=============>................] - ETA: 0s - loss: 0.0583 - accuracy: 0.9870 4352/6993 [=================>............] - ETA: 0s - loss: 0.0547 - accuracy: 0.9867 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0523 - accuracy: 0.9876 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0577 - accuracy: 0.9872 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0582 - accuracy: 0.9871 6912/6993 [============================>.] - ETA: 0s - loss: 0.0572 - accuracy: 0.9870 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0570 - accuracy: 0.9870 - val_loss: 0.6361 - val_accuracy: 0.9252 Epoch 139/199 128/6993 [..............................] - ETA: 0s - loss: 0.0421 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0708 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0566 - accuracy: 0.9872 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0544 - accuracy: 0.9865 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0491 - accuracy: 0.9878 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0553 - accuracy: 0.9868 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0588 - accuracy: 0.9876 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0666 - accuracy: 0.9859 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0649 - accuracy: 0.9859 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0605 - accuracy: 0.9868 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0590 - accuracy: 0.9868 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0684 - accuracy: 0.9860 - val_loss: 0.6068 - val_accuracy: 0.9287 Epoch 140/199 128/6993 [..............................] - ETA: 0s - loss: 0.0207 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0326 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0356 - accuracy: 0.9908 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0397 - accuracy: 0.9893 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0454 - accuracy: 0.9891 3200/6993 [============>.................] - ETA: 0s - loss: 0.0494 - accuracy: 0.9881 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0528 - accuracy: 0.9888 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0571 - accuracy: 0.9888 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0538 - accuracy: 0.9895 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0563 - accuracy: 0.9888 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0599 - accuracy: 0.9881 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0619 - accuracy: 0.9881 - val_loss: 0.6181 - val_accuracy: 0.9211 Epoch 141/199 128/6993 [..............................] - ETA: 0s - loss: 0.0759 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0943 - accuracy: 0.9888 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1279 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1074 - accuracy: 0.9847 3456/6993 [=============>................] - ETA: 0s - loss: 0.0942 - accuracy: 0.9855 4224/6993 [=================>............] - ETA: 0s - loss: 0.0937 - accuracy: 0.9858 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0952 - accuracy: 0.9854 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0934 - accuracy: 0.9847 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0921 - accuracy: 0.9844 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0861 - accuracy: 0.9850 6784/6993 [============================>.] - ETA: 0s - loss: 0.0883 - accuracy: 0.9851 6993/6993 [==============================] - 1s 103us/sample - loss: 0.0911 - accuracy: 0.9848 - val_loss: 0.5216 - val_accuracy: 0.9267 Epoch 142/199 128/6993 [..............................] - ETA: 0s - loss: 0.0281 - accuracy: 0.9922 512/6993 [=>............................] - ETA: 0s - loss: 0.0191 - accuracy: 0.9961 896/6993 [==>...........................] - ETA: 0s - loss: 0.0509 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0630 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0696 - accuracy: 0.9878 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0734 - accuracy: 0.9868 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0723 - accuracy: 0.9878 3456/6993 [=============>................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9876 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0720 - accuracy: 0.9868 4096/6993 [================>.............] - ETA: 0s - loss: 0.0687 - accuracy: 0.9866 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0640 - accuracy: 0.9873 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0662 - accuracy: 0.9875 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0647 - accuracy: 0.9876 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0636 - accuracy: 0.9879 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0604 - accuracy: 0.9882 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0650 - accuracy: 0.9875 6784/6993 [============================>.] - ETA: 0s - loss: 0.0651 - accuracy: 0.9872 6993/6993 [==============================] - 1s 157us/sample - loss: 0.0653 - accuracy: 0.9870 - val_loss: 0.5325 - val_accuracy: 0.9242 Epoch 143/199 128/6993 [..............................] - ETA: 1s - loss: 0.0065 - accuracy: 1.0000 512/6993 [=>............................] - ETA: 1s - loss: 0.0873 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0641 - accuracy: 0.9844 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0770 - accuracy: 0.9831 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0645 - accuracy: 0.9854 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0606 - accuracy: 0.9868 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0523 - accuracy: 0.9885 3200/6993 [============>.................] - ETA: 0s - loss: 0.0505 - accuracy: 0.9884 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0552 - accuracy: 0.9866 3968/6993 [================>.............] - ETA: 0s - loss: 0.0551 - accuracy: 0.9871 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0617 - accuracy: 0.9857 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0608 - accuracy: 0.9862 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0595 - accuracy: 0.9869 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0611 - accuracy: 0.9872 6993/6993 [==============================] - 1s 131us/sample - loss: 0.0635 - accuracy: 0.9871 - val_loss: 0.6425 - val_accuracy: 0.9282 Epoch 144/199 128/6993 [..............................] - ETA: 0s - loss: 0.0137 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0757 - accuracy: 0.9857 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0516 - accuracy: 0.9889 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0514 - accuracy: 0.9890 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0546 - accuracy: 0.9901 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0611 - accuracy: 0.9887 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0611 - accuracy: 0.9877 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0585 - accuracy: 0.9882 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0661 - accuracy: 0.9877 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0686 - accuracy: 0.9876 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0669 - accuracy: 0.9876 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0649 - accuracy: 0.9877 - val_loss: 0.5933 - val_accuracy: 0.9262 Epoch 145/199 128/6993 [..............................] - ETA: 0s - loss: 0.0361 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0790 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0777 - accuracy: 0.9844 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0732 - accuracy: 0.9868 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0668 - accuracy: 0.9867 3200/6993 [============>.................] - ETA: 0s - loss: 0.0664 - accuracy: 0.9859 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0644 - accuracy: 0.9859 4352/6993 [=================>............] - ETA: 0s - loss: 0.0630 - accuracy: 0.9864 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0691 - accuracy: 0.9858 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0673 - accuracy: 0.9862 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0666 - accuracy: 0.9866 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0634 - accuracy: 0.9872 6784/6993 [============================>.] - ETA: 0s - loss: 0.0659 - accuracy: 0.9867 6993/6993 [==============================] - 1s 115us/sample - loss: 0.0648 - accuracy: 0.9868 - val_loss: 0.6183 - val_accuracy: 0.9272 Epoch 146/199 128/6993 [..............................] - ETA: 0s - loss: 0.3878 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.1119 - accuracy: 0.9891 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0874 - accuracy: 0.9898 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0816 - accuracy: 0.9894 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0661 - accuracy: 0.9901 3072/6993 [============>.................] - ETA: 0s - loss: 0.0602 - accuracy: 0.9899 3456/6993 [=============>................] - ETA: 0s - loss: 0.0566 - accuracy: 0.9899 4096/6993 [================>.............] - ETA: 0s - loss: 0.0589 - accuracy: 0.9900 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0601 - accuracy: 0.9897 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0785 - accuracy: 0.9891 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0803 - accuracy: 0.9882 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0800 - accuracy: 0.9866 6784/6993 [============================>.] - ETA: 0s - loss: 0.0788 - accuracy: 0.9869 6993/6993 [==============================] - 1s 118us/sample - loss: 0.0772 - accuracy: 0.9871 - val_loss: 0.5527 - val_accuracy: 0.9338 Epoch 147/199 128/6993 [..............................] - ETA: 0s - loss: 0.0160 - accuracy: 1.0000 640/6993 [=>............................] - ETA: 0s - loss: 0.0289 - accuracy: 0.9937 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0424 - accuracy: 0.9922 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0409 - accuracy: 0.9922 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0438 - accuracy: 0.9913 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0437 - accuracy: 0.9911 3328/6993 [=============>................] - ETA: 0s - loss: 0.0557 - accuracy: 0.9895 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0710 - accuracy: 0.9878 4352/6993 [=================>............] - ETA: 0s - loss: 0.0707 - accuracy: 0.9883 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0652 - accuracy: 0.9889 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0646 - accuracy: 0.9887 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0598 - accuracy: 0.9893 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0677 - accuracy: 0.9886 6993/6993 [==============================] - 1s 108us/sample - loss: 0.0670 - accuracy: 0.9890 - val_loss: 0.5980 - val_accuracy: 0.9262 Epoch 148/199 128/6993 [..............................] - ETA: 0s - loss: 0.0337 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0301 - accuracy: 0.9906 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0480 - accuracy: 0.9883 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0458 - accuracy: 0.9891 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0469 - accuracy: 0.9883 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0573 - accuracy: 0.9857 3456/6993 [=============>................] - ETA: 0s - loss: 0.0553 - accuracy: 0.9855 3968/6993 [================>.............] - ETA: 0s - loss: 0.0582 - accuracy: 0.9849 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0572 - accuracy: 0.9848 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0545 - accuracy: 0.9855 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0558 - accuracy: 0.9858 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0668 - accuracy: 0.9850 6993/6993 [==============================] - 1s 105us/sample - loss: 0.0663 - accuracy: 0.9851 - val_loss: 0.6540 - val_accuracy: 0.9292 Epoch 149/199 128/6993 [..............................] - ETA: 0s - loss: 0.0219 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0339 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0706 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0786 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0774 - accuracy: 0.9851 3328/6993 [=============>................] - ETA: 0s - loss: 0.0684 - accuracy: 0.9865 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0692 - accuracy: 0.9868 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0678 - accuracy: 0.9870 3968/6993 [================>.............] - ETA: 0s - loss: 0.0704 - accuracy: 0.9871 4096/6993 [================>.............] - ETA: 0s - loss: 0.0691 - accuracy: 0.9873 4352/6993 [=================>............] - ETA: 0s - loss: 0.0690 - accuracy: 0.9874 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0663 - accuracy: 0.9874 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0643 - accuracy: 0.9877 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0655 - accuracy: 0.9871 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0646 - accuracy: 0.9870 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0634 - accuracy: 0.9872 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0634 - accuracy: 0.9873 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0656 - accuracy: 0.9867 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0662 - accuracy: 0.9864 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0647 - accuracy: 0.9868 6784/6993 [============================>.] - ETA: 0s - loss: 0.0639 - accuracy: 0.9870 6993/6993 [==============================] - 2s 252us/sample - loss: 0.0638 - accuracy: 0.9870 - val_loss: 0.5852 - val_accuracy: 0.9297 Epoch 150/199 128/6993 [..............................] - ETA: 1s - loss: 0.0188 - accuracy: 0.9922 384/6993 [>.............................] - ETA: 1s - loss: 0.0318 - accuracy: 0.9896 768/6993 [==>...........................] - ETA: 1s - loss: 0.0336 - accuracy: 0.9870 1024/6993 [===>..........................] - ETA: 1s - loss: 0.0281 - accuracy: 0.9883 1280/6993 [====>.........................] - ETA: 1s - loss: 0.0367 - accuracy: 0.9867 1408/6993 [=====>........................] - ETA: 1s - loss: 0.0382 - accuracy: 0.9865 1792/6993 [======>.......................] - ETA: 1s - loss: 0.0354 - accuracy: 0.9883 2176/6993 [========>.....................] - ETA: 1s - loss: 0.0491 - accuracy: 0.9867 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0554 - accuracy: 0.9859 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0560 - accuracy: 0.9861 3200/6993 [============>.................] - ETA: 0s - loss: 0.0624 - accuracy: 0.9856 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0642 - accuracy: 0.9860 3968/6993 [================>.............] - ETA: 0s - loss: 0.0615 - accuracy: 0.9859 4224/6993 [=================>............] - ETA: 0s - loss: 0.0586 - accuracy: 0.9865 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0576 - accuracy: 0.9865 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0592 - accuracy: 0.9861 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0579 - accuracy: 0.9865 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0594 - accuracy: 0.9865 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0609 - accuracy: 0.9862 6993/6993 [==============================] - 1s 171us/sample - loss: 0.0626 - accuracy: 0.9860 - val_loss: 0.5912 - val_accuracy: 0.9282 Epoch 151/199 128/6993 [..............................] - ETA: 0s - loss: 0.1137 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0538 - accuracy: 0.9911 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0735 - accuracy: 0.9892 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0686 - accuracy: 0.9894 3072/6993 [============>.................] - ETA: 0s - loss: 0.0599 - accuracy: 0.9899 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0528 - accuracy: 0.9901 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0513 - accuracy: 0.9896 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0501 - accuracy: 0.9893 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0492 - accuracy: 0.9890 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0491 - accuracy: 0.9887 - val_loss: 0.6912 - val_accuracy: 0.9277 Epoch 152/199 128/6993 [..............................] - ETA: 0s - loss: 0.0770 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0586 - accuracy: 0.9877 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0717 - accuracy: 0.9857 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0796 - accuracy: 0.9857 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0656 - accuracy: 0.9868 3456/6993 [=============>................] - ETA: 0s - loss: 0.0714 - accuracy: 0.9864 4096/6993 [================>.............] - ETA: 0s - loss: 0.0697 - accuracy: 0.9873 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0731 - accuracy: 0.9873 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0859 - accuracy: 0.9862 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0834 - accuracy: 0.9860 6912/6993 [============================>.] - ETA: 0s - loss: 0.0823 - accuracy: 0.9863 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0818 - accuracy: 0.9863 - val_loss: 0.6162 - val_accuracy: 0.9216 Epoch 153/199 128/6993 [..............................] - ETA: 0s - loss: 0.0719 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0611 - accuracy: 0.9896 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0844 - accuracy: 0.9837 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0839 - accuracy: 0.9835 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0690 - accuracy: 0.9857 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0673 - accuracy: 0.9869 4224/6993 [=================>............] - ETA: 0s - loss: 0.0833 - accuracy: 0.9860 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0813 - accuracy: 0.9858 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0813 - accuracy: 0.9849 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0764 - accuracy: 0.9850 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0775 - accuracy: 0.9844 - val_loss: 0.5283 - val_accuracy: 0.9272 Epoch 154/199 128/6993 [..............................] - ETA: 0s - loss: 0.2444 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1114 - accuracy: 0.9821 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0809 - accuracy: 0.9874 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0607 - accuracy: 0.9901 3200/6993 [============>.................] - ETA: 0s - loss: 0.0655 - accuracy: 0.9909 3968/6993 [================>.............] - ETA: 0s - loss: 0.0661 - accuracy: 0.9904 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0726 - accuracy: 0.9901 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0769 - accuracy: 0.9892 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0811 - accuracy: 0.9887 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0792 - accuracy: 0.9888 - val_loss: 0.6449 - val_accuracy: 0.9267 Epoch 155/199 128/6993 [..............................] - ETA: 0s - loss: 0.0226 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0388 - accuracy: 0.9933 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0473 - accuracy: 0.9910 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0473 - accuracy: 0.9897 3200/6993 [============>.................] - ETA: 0s - loss: 0.0563 - accuracy: 0.9875 3968/6993 [================>.............] - ETA: 0s - loss: 0.0532 - accuracy: 0.9882 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0532 - accuracy: 0.9881 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0583 - accuracy: 0.9870 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0666 - accuracy: 0.9862 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0673 - accuracy: 0.9858 - val_loss: 0.5697 - val_accuracy: 0.9277 Epoch 156/199 128/6993 [..............................] - ETA: 0s - loss: 0.1163 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0522 - accuracy: 0.9870 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0482 - accuracy: 0.9868 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0633 - accuracy: 0.9840 3200/6993 [============>.................] - ETA: 0s - loss: 0.0618 - accuracy: 0.9844 3968/6993 [================>.............] - ETA: 0s - loss: 0.0824 - accuracy: 0.9836 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0819 - accuracy: 0.9833 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0783 - accuracy: 0.9838 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0717 - accuracy: 0.9850 6993/6993 [==============================] - 1s 83us/sample - loss: 0.0720 - accuracy: 0.9850 - val_loss: 0.5922 - val_accuracy: 0.9262 Epoch 157/199 128/6993 [..............................] - ETA: 0s - loss: 0.0508 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0395 - accuracy: 0.9900 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0490 - accuracy: 0.9892 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0512 - accuracy: 0.9896 3072/6993 [============>.................] - ETA: 0s - loss: 0.0527 - accuracy: 0.9902 3968/6993 [================>.............] - ETA: 0s - loss: 0.0458 - accuracy: 0.9912 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0548 - accuracy: 0.9894 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0508 - accuracy: 0.9898 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0550 - accuracy: 0.9894 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0551 - accuracy: 0.9890 - val_loss: 0.6715 - val_accuracy: 0.9206 Epoch 158/199 128/6993 [..............................] - ETA: 0s - loss: 0.0180 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0723 - accuracy: 0.9854 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0632 - accuracy: 0.9883 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0553 - accuracy: 0.9889 3200/6993 [============>.................] - ETA: 0s - loss: 0.0514 - accuracy: 0.9894 3968/6993 [================>.............] - ETA: 0s - loss: 0.0575 - accuracy: 0.9889 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0601 - accuracy: 0.9881 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0656 - accuracy: 0.9875 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0728 - accuracy: 0.9870 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0711 - accuracy: 0.9869 6784/6993 [============================>.] - ETA: 0s - loss: 0.0701 - accuracy: 0.9870 6993/6993 [==============================] - 1s 105us/sample - loss: 0.0732 - accuracy: 0.9864 - val_loss: 0.6786 - val_accuracy: 0.9262 Epoch 159/199 128/6993 [..............................] - ETA: 0s - loss: 0.0218 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0633 - accuracy: 0.9870 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0565 - accuracy: 0.9902 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0735 - accuracy: 0.9883 3072/6993 [============>.................] - ETA: 0s - loss: 0.0748 - accuracy: 0.9883 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0751 - accuracy: 0.9887 4352/6993 [=================>............] - ETA: 0s - loss: 0.0691 - accuracy: 0.9894 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0658 - accuracy: 0.9899 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0638 - accuracy: 0.9898 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0597 - accuracy: 0.9899 6784/6993 [============================>.] - ETA: 0s - loss: 0.0577 - accuracy: 0.9897 6993/6993 [==============================] - 1s 97us/sample - loss: 0.0595 - accuracy: 0.9896 - val_loss: 0.6063 - val_accuracy: 0.9292 Epoch 160/199 128/6993 [..............................] - ETA: 0s - loss: 0.0401 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0502 - accuracy: 0.9844 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0829 - accuracy: 0.9808 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0723 - accuracy: 0.9835 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0592 - accuracy: 0.9861 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0621 - accuracy: 0.9866 4352/6993 [=================>............] - ETA: 0s - loss: 0.0563 - accuracy: 0.9871 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0646 - accuracy: 0.9861 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0653 - accuracy: 0.9864 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0659 - accuracy: 0.9865 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0760 - accuracy: 0.9861 - val_loss: 0.6931 - val_accuracy: 0.9221 Epoch 161/199 128/6993 [..............................] - ETA: 0s - loss: 0.0208 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0765 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0746 - accuracy: 0.9832 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0698 - accuracy: 0.9852 3200/6993 [============>.................] - ETA: 0s - loss: 0.0725 - accuracy: 0.9872 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0705 - accuracy: 0.9876 4352/6993 [=================>............] - ETA: 0s - loss: 0.0721 - accuracy: 0.9874 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0744 - accuracy: 0.9875 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0713 - accuracy: 0.9874 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0698 - accuracy: 0.9871 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0688 - accuracy: 0.9876 - val_loss: 0.5611 - val_accuracy: 0.9312 Epoch 162/199 128/6993 [..............................] - ETA: 0s - loss: 0.0292 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0475 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0547 - accuracy: 0.9886 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0665 - accuracy: 0.9885 3072/6993 [============>.................] - ETA: 0s - loss: 0.0639 - accuracy: 0.9896 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0680 - accuracy: 0.9888 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0667 - accuracy: 0.9889 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0687 - accuracy: 0.9877 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0731 - accuracy: 0.9874 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0718 - accuracy: 0.9876 - val_loss: 0.5458 - val_accuracy: 0.9267 Epoch 163/199 128/6993 [..............................] - ETA: 0s - loss: 0.0206 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0187 - accuracy: 0.9961 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0325 - accuracy: 0.9943 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0554 - accuracy: 0.9903 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0819 - accuracy: 0.9886 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0772 - accuracy: 0.9874 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0877 - accuracy: 0.9879 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0801 - accuracy: 0.9885 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0852 - accuracy: 0.9870 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0834 - accuracy: 0.9874 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0815 - accuracy: 0.9870 - val_loss: 0.5688 - val_accuracy: 0.9307 Epoch 164/199 128/6993 [..............................] - ETA: 0s - loss: 0.0611 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0759 - accuracy: 0.9821 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1085 - accuracy: 0.9826 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1042 - accuracy: 0.9844 3072/6993 [============>.................] - ETA: 0s - loss: 0.1039 - accuracy: 0.9840 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0932 - accuracy: 0.9844 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0933 - accuracy: 0.9839 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0969 - accuracy: 0.9838 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0936 - accuracy: 0.9845 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0886 - accuracy: 0.9844 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0848 - accuracy: 0.9850 - val_loss: 0.5787 - val_accuracy: 0.9363 Epoch 165/199 128/6993 [..............................] - ETA: 0s - loss: 0.0049 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0411 - accuracy: 0.9896 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0391 - accuracy: 0.9883 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0527 - accuracy: 0.9887 3072/6993 [============>.................] - ETA: 0s - loss: 0.0575 - accuracy: 0.9886 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0549 - accuracy: 0.9885 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0534 - accuracy: 0.9894 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0659 - accuracy: 0.9885 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0638 - accuracy: 0.9883 6912/6993 [============================>.] - ETA: 0s - loss: 0.0603 - accuracy: 0.9887 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0601 - accuracy: 0.9886 - val_loss: 0.7191 - val_accuracy: 0.9257 Epoch 166/199 128/6993 [..............................] - ETA: 0s - loss: 0.1201 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0634 - accuracy: 0.9888 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0739 - accuracy: 0.9868 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0686 - accuracy: 0.9873 3200/6993 [============>.................] - ETA: 0s - loss: 0.0683 - accuracy: 0.9872 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0603 - accuracy: 0.9880 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0590 - accuracy: 0.9881 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0551 - accuracy: 0.9885 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0715 - accuracy: 0.9875 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0844 - accuracy: 0.9874 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0815 - accuracy: 0.9873 - val_loss: 0.6661 - val_accuracy: 0.9226 Epoch 167/199 128/6993 [..............................] - ETA: 0s - loss: 0.0541 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0433 - accuracy: 0.9922 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0409 - accuracy: 0.9896 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0352 - accuracy: 0.9905 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0490 - accuracy: 0.9865 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0438 - accuracy: 0.9878 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0456 - accuracy: 0.9881 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0521 - accuracy: 0.9873 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0559 - accuracy: 0.9876 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0564 - accuracy: 0.9874 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0572 - accuracy: 0.9878 6912/6993 [============================>.] - ETA: 0s - loss: 0.0542 - accuracy: 0.9884 6993/6993 [==============================] - 1s 103us/sample - loss: 0.0540 - accuracy: 0.9886 - val_loss: 0.6716 - val_accuracy: 0.9272 Epoch 168/199 128/6993 [..............................] - ETA: 0s - loss: 0.0205 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0902 - accuracy: 0.9891 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1341 - accuracy: 0.9859 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1292 - accuracy: 0.9839 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1066 - accuracy: 0.9859 3200/6993 [============>.................] - ETA: 0s - loss: 0.1124 - accuracy: 0.9834 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1020 - accuracy: 0.9852 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0947 - accuracy: 0.9857 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0948 - accuracy: 0.9852 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0896 - accuracy: 0.9854 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0852 - accuracy: 0.9857 6784/6993 [============================>.] - ETA: 0s - loss: 0.0856 - accuracy: 0.9854 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0843 - accuracy: 0.9854 - val_loss: 0.6903 - val_accuracy: 0.9237 Epoch 169/199 128/6993 [..............................] - ETA: 0s - loss: 0.0654 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0438 - accuracy: 0.9900 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0438 - accuracy: 0.9889 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0785 - accuracy: 0.9881 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0667 - accuracy: 0.9888 3456/6993 [=============>................] - ETA: 0s - loss: 0.0624 - accuracy: 0.9896 4096/6993 [================>.............] - ETA: 0s - loss: 0.0669 - accuracy: 0.9885 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0626 - accuracy: 0.9883 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0628 - accuracy: 0.9881 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0619 - accuracy: 0.9883 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0589 - accuracy: 0.9884 - val_loss: 0.7622 - val_accuracy: 0.9262 Epoch 170/199 128/6993 [..............................] - ETA: 0s - loss: 0.3553 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1329 - accuracy: 0.9833 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1212 - accuracy: 0.9814 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1246 - accuracy: 0.9819 3200/6993 [============>.................] - ETA: 0s - loss: 0.0992 - accuracy: 0.9850 3968/6993 [================>.............] - ETA: 0s - loss: 0.1020 - accuracy: 0.9851 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0933 - accuracy: 0.9850 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0959 - accuracy: 0.9842 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1006 - accuracy: 0.9839 6912/6993 [============================>.] - ETA: 0s - loss: 0.0948 - accuracy: 0.9847 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0941 - accuracy: 0.9847 - val_loss: 0.5734 - val_accuracy: 0.9297 Epoch 171/199 128/6993 [..............................] - ETA: 0s - loss: 0.1700 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0545 - accuracy: 0.9896 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0669 - accuracy: 0.9892 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0560 - accuracy: 0.9891 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0503 - accuracy: 0.9904 3328/6993 [=============>................] - ETA: 0s - loss: 0.0537 - accuracy: 0.9907 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0523 - accuracy: 0.9906 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0468 - accuracy: 0.9915 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0493 - accuracy: 0.9914 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0557 - accuracy: 0.9907 6784/6993 [============================>.] - ETA: 0s - loss: 0.0618 - accuracy: 0.9897 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0602 - accuracy: 0.9898 - val_loss: 0.7462 - val_accuracy: 0.9297 Epoch 172/199 128/6993 [..............................] - ETA: 0s - loss: 0.0318 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0551 - accuracy: 0.9922 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0484 - accuracy: 0.9922 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0596 - accuracy: 0.9908 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0658 - accuracy: 0.9891 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0600 - accuracy: 0.9897 4224/6993 [=================>............] - ETA: 0s - loss: 0.0756 - accuracy: 0.9889 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0715 - accuracy: 0.9885 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0672 - accuracy: 0.9886 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0731 - accuracy: 0.9881 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0727 - accuracy: 0.9883 - val_loss: 0.7152 - val_accuracy: 0.9262 Epoch 173/199 128/6993 [..............................] - ETA: 0s - loss: 0.0938 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0344 - accuracy: 0.9906 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0414 - accuracy: 0.9883 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0665 - accuracy: 0.9854 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0699 - accuracy: 0.9874 3200/6993 [============>.................] - ETA: 0s - loss: 0.0619 - accuracy: 0.9878 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0665 - accuracy: 0.9870 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0679 - accuracy: 0.9873 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0705 - accuracy: 0.9875 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0711 - accuracy: 0.9877 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0715 - accuracy: 0.9879 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0745 - accuracy: 0.9877 6912/6993 [============================>.] - ETA: 0s - loss: 0.0709 - accuracy: 0.9884 6993/6993 [==============================] - 1s 110us/sample - loss: 0.0701 - accuracy: 0.9886 - val_loss: 0.6520 - val_accuracy: 0.9292 Epoch 174/199 128/6993 [..............................] - ETA: 0s - loss: 0.0186 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1580 - accuracy: 0.9844 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1282 - accuracy: 0.9836 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1118 - accuracy: 0.9855 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1059 - accuracy: 0.9865 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1168 - accuracy: 0.9854 3328/6993 [=============>................] - ETA: 0s - loss: 0.1017 - accuracy: 0.9868 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0936 - accuracy: 0.9870 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0874 - accuracy: 0.9868 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0791 - accuracy: 0.9875 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0747 - accuracy: 0.9879 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0728 - accuracy: 0.9884 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0709 - accuracy: 0.9883 6993/6993 [==============================] - 1s 115us/sample - loss: 0.0701 - accuracy: 0.9884 - val_loss: 0.8073 - val_accuracy: 0.9353 Epoch 175/199 128/6993 [..............................] - ETA: 1s - loss: 0.0386 - accuracy: 0.9844 512/6993 [=>............................] - ETA: 1s - loss: 0.0801 - accuracy: 0.9883 896/6993 [==>...........................] - ETA: 0s - loss: 0.0923 - accuracy: 0.9855 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1182 - accuracy: 0.9836 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0962 - accuracy: 0.9855 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0997 - accuracy: 0.9852 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0882 - accuracy: 0.9857 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0925 - accuracy: 0.9863 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0839 - accuracy: 0.9866 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0959 - accuracy: 0.9863 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0942 - accuracy: 0.9861 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0886 - accuracy: 0.9870 6993/6993 [==============================] - 1s 105us/sample - loss: 0.0866 - accuracy: 0.9868 - val_loss: 0.7325 - val_accuracy: 0.9287 Epoch 176/199 128/6993 [..............................] - ETA: 0s - loss: 0.0893 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.1139 - accuracy: 0.9844 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0871 - accuracy: 0.9852 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0709 - accuracy: 0.9877 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0699 - accuracy: 0.9889 3072/6993 [============>.................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9870 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0637 - accuracy: 0.9881 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0640 - accuracy: 0.9875 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0676 - accuracy: 0.9870 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0630 - accuracy: 0.9875 6784/6993 [============================>.] - ETA: 0s - loss: 0.0612 - accuracy: 0.9875 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0607 - accuracy: 0.9876 - val_loss: 0.8169 - val_accuracy: 0.9282 Epoch 177/199 128/6993 [..............................] - ETA: 0s - loss: 0.0247 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0364 - accuracy: 0.9870 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0555 - accuracy: 0.9865 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0614 - accuracy: 0.9849 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0637 - accuracy: 0.9870 3328/6993 [=============>................] - ETA: 0s - loss: 0.0611 - accuracy: 0.9874 4096/6993 [================>.............] - ETA: 0s - loss: 0.0609 - accuracy: 0.9866 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0573 - accuracy: 0.9878 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0534 - accuracy: 0.9877 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0587 - accuracy: 0.9876 6784/6993 [============================>.] - ETA: 0s - loss: 0.0550 - accuracy: 0.9879 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0544 - accuracy: 0.9881 - val_loss: 0.7300 - val_accuracy: 0.9312 Epoch 178/199 128/6993 [..............................] - ETA: 0s - loss: 0.1584 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.0992 - accuracy: 0.9866 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0737 - accuracy: 0.9876 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0622 - accuracy: 0.9885 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0837 - accuracy: 0.9879 3456/6993 [=============>................] - ETA: 0s - loss: 0.0824 - accuracy: 0.9890 4224/6993 [=================>............] - ETA: 0s - loss: 0.0815 - accuracy: 0.9877 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0972 - accuracy: 0.9862 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0877 - accuracy: 0.9875 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0934 - accuracy: 0.9876 6912/6993 [============================>.] - ETA: 0s - loss: 0.0920 - accuracy: 0.9873 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0921 - accuracy: 0.9870 - val_loss: 0.7172 - val_accuracy: 0.9282 Epoch 179/199 128/6993 [..............................] - ETA: 0s - loss: 0.0349 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0266 - accuracy: 0.9948 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0517 - accuracy: 0.9908 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0488 - accuracy: 0.9907 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0559 - accuracy: 0.9911 3456/6993 [=============>................] - ETA: 0s - loss: 0.0672 - accuracy: 0.9905 4096/6993 [================>.............] - ETA: 0s - loss: 0.0684 - accuracy: 0.9902 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0697 - accuracy: 0.9905 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0757 - accuracy: 0.9895 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0718 - accuracy: 0.9894 6784/6993 [============================>.] - ETA: 0s - loss: 0.0746 - accuracy: 0.9888 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0727 - accuracy: 0.9890 - val_loss: 0.7056 - val_accuracy: 0.9323 Epoch 180/199 128/6993 [..............................] - ETA: 0s - loss: 0.0106 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.1166 - accuracy: 0.9788 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0972 - accuracy: 0.9820 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0951 - accuracy: 0.9836 3072/6993 [============>.................] - ETA: 0s - loss: 0.0944 - accuracy: 0.9840 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0876 - accuracy: 0.9846 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0832 - accuracy: 0.9848 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0898 - accuracy: 0.9844 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0843 - accuracy: 0.9845 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0804 - accuracy: 0.9845 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0754 - accuracy: 0.9853 - val_loss: 0.6690 - val_accuracy: 0.9302 Epoch 181/199 128/6993 [..............................] - ETA: 0s - loss: 0.0020 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0793 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0614 - accuracy: 0.9915 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0482 - accuracy: 0.9917 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0406 - accuracy: 0.9918 3456/6993 [=============>................] - ETA: 0s - loss: 0.0648 - accuracy: 0.9893 4096/6993 [================>.............] - ETA: 0s - loss: 0.0688 - accuracy: 0.9888 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0650 - accuracy: 0.9883 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0689 - accuracy: 0.9878 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0701 - accuracy: 0.9878 6784/6993 [============================>.] - ETA: 0s - loss: 0.0681 - accuracy: 0.9881 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0673 - accuracy: 0.9880 - val_loss: 0.6913 - val_accuracy: 0.9292 Epoch 182/199 128/6993 [..............................] - ETA: 0s - loss: 0.0332 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0654 - accuracy: 0.9896 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0566 - accuracy: 0.9883 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0786 - accuracy: 0.9896 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0719 - accuracy: 0.9895 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0629 - accuracy: 0.9897 4224/6993 [=================>............] - ETA: 0s - loss: 0.0636 - accuracy: 0.9893 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0674 - accuracy: 0.9876 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0698 - accuracy: 0.9879 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0656 - accuracy: 0.9880 6912/6993 [============================>.] - ETA: 0s - loss: 0.0636 - accuracy: 0.9881 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0634 - accuracy: 0.9880 - val_loss: 0.6802 - val_accuracy: 0.9307 Epoch 183/199 128/6993 [..............................] - ETA: 0s - loss: 0.1233 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0512 - accuracy: 0.9922 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0489 - accuracy: 0.9896 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0491 - accuracy: 0.9899 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0494 - accuracy: 0.9907 3200/6993 [============>.................] - ETA: 0s - loss: 0.0464 - accuracy: 0.9906 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0510 - accuracy: 0.9908 4224/6993 [=================>............] - ETA: 0s - loss: 0.0531 - accuracy: 0.9903 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0510 - accuracy: 0.9899 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0528 - accuracy: 0.9893 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0533 - accuracy: 0.9892 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0553 - accuracy: 0.9893 6993/6993 [==============================] - 1s 110us/sample - loss: 0.0646 - accuracy: 0.9884 - val_loss: 0.7370 - val_accuracy: 0.9292 Epoch 184/199 128/6993 [..............................] - ETA: 1s - loss: 0.0440 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0146 - accuracy: 0.9948 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0361 - accuracy: 0.9943 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0438 - accuracy: 0.9917 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0576 - accuracy: 0.9907 3328/6993 [=============>................] - ETA: 0s - loss: 0.0678 - accuracy: 0.9892 3968/6993 [================>.............] - ETA: 0s - loss: 0.0643 - accuracy: 0.9892 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0582 - accuracy: 0.9898 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0526 - accuracy: 0.9907 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0545 - accuracy: 0.9905 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0550 - accuracy: 0.9904 6912/6993 [============================>.] - ETA: 0s - loss: 0.0676 - accuracy: 0.9897 6993/6993 [==============================] - 1s 99us/sample - loss: 0.0669 - accuracy: 0.9898 - val_loss: 0.7832 - val_accuracy: 0.9343 Epoch 185/199 128/6993 [..............................] - ETA: 0s - loss: 0.0101 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0628 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1025 - accuracy: 0.9858 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0804 - accuracy: 0.9858 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0821 - accuracy: 0.9851 3456/6993 [=============>................] - ETA: 0s - loss: 0.0878 - accuracy: 0.9841 4096/6993 [================>.............] - ETA: 0s - loss: 0.0772 - accuracy: 0.9854 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0761 - accuracy: 0.9854 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0787 - accuracy: 0.9855 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0704 - accuracy: 0.9869 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0687 - accuracy: 0.9870 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0659 - accuracy: 0.9876 - val_loss: 0.7705 - val_accuracy: 0.9328 Epoch 186/199 128/6993 [..............................] - ETA: 1s - loss: 0.0194 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0424 - accuracy: 0.9870 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0384 - accuracy: 0.9879 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0764 - accuracy: 0.9873 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0783 - accuracy: 0.9870 3328/6993 [=============>................] - ETA: 0s - loss: 0.0705 - accuracy: 0.9877 3968/6993 [================>.............] - ETA: 0s - loss: 0.0744 - accuracy: 0.9864 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0696 - accuracy: 0.9870 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0852 - accuracy: 0.9876 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0837 - accuracy: 0.9868 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0799 - accuracy: 0.9867 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0777 - accuracy: 0.9870 - val_loss: 0.6726 - val_accuracy: 0.9328 Epoch 187/199 128/6993 [..............................] - ETA: 0s - loss: 0.1050 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0540 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0938 - accuracy: 0.9872 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0778 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0678 - accuracy: 0.9881 3328/6993 [=============>................] - ETA: 0s - loss: 0.0700 - accuracy: 0.9880 4096/6993 [================>.............] - ETA: 0s - loss: 0.0667 - accuracy: 0.9871 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0653 - accuracy: 0.9875 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0617 - accuracy: 0.9885 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0616 - accuracy: 0.9875 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0621 - accuracy: 0.9876 6993/6993 [==============================] - 1s 97us/sample - loss: 0.0627 - accuracy: 0.9874 - val_loss: 0.6589 - val_accuracy: 0.9368 Epoch 188/199 128/6993 [..............................] - ETA: 0s - loss: 0.0102 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0425 - accuracy: 0.9933 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0817 - accuracy: 0.9922 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0775 - accuracy: 0.9885 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0759 - accuracy: 0.9881 3200/6993 [============>.................] - ETA: 0s - loss: 0.0689 - accuracy: 0.9887 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0691 - accuracy: 0.9888 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0633 - accuracy: 0.9895 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0607 - accuracy: 0.9896 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0578 - accuracy: 0.9899 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0582 - accuracy: 0.9896 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0647 - accuracy: 0.9883 - val_loss: 0.7233 - val_accuracy: 0.9287 Epoch 189/199 128/6993 [..............................] - ETA: 0s - loss: 0.1673 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.0508 - accuracy: 0.9891 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0465 - accuracy: 0.9875 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0437 - accuracy: 0.9885 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0491 - accuracy: 0.9875 3200/6993 [============>.................] - ETA: 0s - loss: 0.0502 - accuracy: 0.9881 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0665 - accuracy: 0.9878 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0753 - accuracy: 0.9884 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0716 - accuracy: 0.9887 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0685 - accuracy: 0.9889 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0661 - accuracy: 0.9889 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0722 - accuracy: 0.9887 - val_loss: 0.8132 - val_accuracy: 0.9242 Epoch 190/199 128/6993 [..............................] - ETA: 0s - loss: 0.0363 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0575 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0763 - accuracy: 0.9879 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0650 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0620 - accuracy: 0.9881 3200/6993 [============>.................] - ETA: 0s - loss: 0.0578 - accuracy: 0.9887 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0551 - accuracy: 0.9890 4352/6993 [=================>............] - ETA: 0s - loss: 0.0551 - accuracy: 0.9890 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0721 - accuracy: 0.9872 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0890 - accuracy: 0.9876 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0856 - accuracy: 0.9879 6912/6993 [============================>.] - ETA: 0s - loss: 0.0830 - accuracy: 0.9877 6993/6993 [==============================] - 1s 97us/sample - loss: 0.0825 - accuracy: 0.9876 - val_loss: 0.8143 - val_accuracy: 0.9317 Epoch 191/199 128/6993 [..............................] - ETA: 0s - loss: 0.1311 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0622 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0369 - accuracy: 0.9936 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0475 - accuracy: 0.9922 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0411 - accuracy: 0.9922 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0443 - accuracy: 0.9922 3456/6993 [=============>................] - ETA: 0s - loss: 0.0565 - accuracy: 0.9899 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0585 - accuracy: 0.9891 4352/6993 [=================>............] - ETA: 0s - loss: 0.0734 - accuracy: 0.9885 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0704 - accuracy: 0.9881 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0680 - accuracy: 0.9883 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0661 - accuracy: 0.9882 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0690 - accuracy: 0.9886 6993/6993 [==============================] - 1s 116us/sample - loss: 0.0703 - accuracy: 0.9888 - val_loss: 0.7538 - val_accuracy: 0.9328 Epoch 192/199 128/6993 [..............................] - ETA: 1s - loss: 0.0053 - accuracy: 1.0000 640/6993 [=>............................] - ETA: 0s - loss: 0.0576 - accuracy: 0.9906 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0480 - accuracy: 0.9891 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0806 - accuracy: 0.9870 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0785 - accuracy: 0.9877 3328/6993 [=============>................] - ETA: 0s - loss: 0.0751 - accuracy: 0.9871 3968/6993 [================>.............] - ETA: 0s - loss: 0.0658 - accuracy: 0.9882 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0689 - accuracy: 0.9887 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0689 - accuracy: 0.9888 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0705 - accuracy: 0.9888 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0717 - accuracy: 0.9884 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0720 - accuracy: 0.9876 - val_loss: 0.7675 - val_accuracy: 0.9277 Epoch 193/199 128/6993 [..............................] - ETA: 0s - loss: 0.0191 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0578 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0440 - accuracy: 0.9872 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0412 - accuracy: 0.9897 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0471 - accuracy: 0.9888 3328/6993 [=============>................] - ETA: 0s - loss: 0.0477 - accuracy: 0.9892 3968/6993 [================>.............] - ETA: 0s - loss: 0.0501 - accuracy: 0.9889 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0550 - accuracy: 0.9877 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0602 - accuracy: 0.9876 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0584 - accuracy: 0.9874 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0586 - accuracy: 0.9877 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0589 - accuracy: 0.9871 6993/6993 [==============================] - 1s 99us/sample - loss: 0.0580 - accuracy: 0.9871 - val_loss: 0.8556 - val_accuracy: 0.9323 Epoch 194/199 128/6993 [..............................] - ETA: 0s - loss: 0.0114 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0605 - accuracy: 0.9844 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0788 - accuracy: 0.9850 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0950 - accuracy: 0.9862 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0835 - accuracy: 0.9876 3456/6993 [=============>................] - ETA: 0s - loss: 0.0732 - accuracy: 0.9878 4096/6993 [================>.............] - ETA: 0s - loss: 0.0735 - accuracy: 0.9873 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0908 - accuracy: 0.9871 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0828 - accuracy: 0.9877 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0915 - accuracy: 0.9880 6784/6993 [============================>.] - ETA: 0s - loss: 0.0945 - accuracy: 0.9872 6993/6993 [==============================] - 1s 91us/sample - loss: 0.1053 - accuracy: 0.9871 - val_loss: 0.6925 - val_accuracy: 0.9242 Epoch 195/199 128/6993 [..............................] - ETA: 0s - loss: 0.0310 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0834 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0709 - accuracy: 0.9893 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0581 - accuracy: 0.9907 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0683 - accuracy: 0.9900 3328/6993 [=============>................] - ETA: 0s - loss: 0.0666 - accuracy: 0.9892 3968/6993 [================>.............] - ETA: 0s - loss: 0.0662 - accuracy: 0.9899 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0617 - accuracy: 0.9894 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0593 - accuracy: 0.9888 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0587 - accuracy: 0.9885 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0543 - accuracy: 0.9890 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0525 - accuracy: 0.9893 - val_loss: 0.7575 - val_accuracy: 0.9247 Epoch 196/199 128/6993 [..............................] - ETA: 0s - loss: 0.0241 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0591 - accuracy: 0.9877 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0641 - accuracy: 0.9889 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0670 - accuracy: 0.9890 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0563 - accuracy: 0.9901 3456/6993 [=============>................] - ETA: 0s - loss: 0.0640 - accuracy: 0.9896 4096/6993 [================>.............] - ETA: 0s - loss: 0.0594 - accuracy: 0.9895 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0540 - accuracy: 0.9892 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0584 - accuracy: 0.9888 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0577 - accuracy: 0.9890 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0563 - accuracy: 0.9893 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0564 - accuracy: 0.9890 - val_loss: 0.7239 - val_accuracy: 0.9262 Epoch 197/199 128/6993 [..............................] - ETA: 0s - loss: 0.0119 - accuracy: 1.0000 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0705 - accuracy: 0.9883 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0618 - accuracy: 0.9886 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0598 - accuracy: 0.9883 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0605 - accuracy: 0.9872 3328/6993 [=============>................] - ETA: 0s - loss: 0.0535 - accuracy: 0.9883 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0481 - accuracy: 0.9891 4352/6993 [=================>............] - ETA: 0s - loss: 0.0429 - accuracy: 0.9903 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0414 - accuracy: 0.9903 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0424 - accuracy: 0.9899 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0453 - accuracy: 0.9898 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0450 - accuracy: 0.9895 6784/6993 [============================>.] - ETA: 0s - loss: 0.0548 - accuracy: 0.9888 6993/6993 [==============================] - 1s 112us/sample - loss: 0.0554 - accuracy: 0.9887 - val_loss: 0.7904 - val_accuracy: 0.9282 Epoch 198/199 128/6993 [..............................] - ETA: 0s - loss: 0.0798 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1035 - accuracy: 0.9870 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0877 - accuracy: 0.9870 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0749 - accuracy: 0.9876 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0662 - accuracy: 0.9885 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0579 - accuracy: 0.9891 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0558 - accuracy: 0.9888 3200/6993 [============>.................] - ETA: 0s - loss: 0.0650 - accuracy: 0.9884 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0697 - accuracy: 0.9886 4096/6993 [================>.............] - ETA: 0s - loss: 0.0626 - accuracy: 0.9893 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0649 - accuracy: 0.9896 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0636 - accuracy: 0.9891 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0652 - accuracy: 0.9883 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0660 - accuracy: 0.9882 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0656 - accuracy: 0.9883 6784/6993 [============================>.] - ETA: 0s - loss: 0.0644 - accuracy: 0.9885 6993/6993 [==============================] - 1s 142us/sample - loss: 0.0628 - accuracy: 0.9888 - val_loss: 0.7639 - val_accuracy: 0.9252 Epoch 199/199 128/6993 [..............................] - ETA: 0s - loss: 0.0656 - accuracy: 0.9766 512/6993 [=>............................] - ETA: 0s - loss: 0.0932 - accuracy: 0.9883 896/6993 [==>...........................] - ETA: 0s - loss: 0.0645 - accuracy: 0.9900 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0586 - accuracy: 0.9891 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0731 - accuracy: 0.9876 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0600 - accuracy: 0.9896 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0552 - accuracy: 0.9900 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0550 - accuracy: 0.9888 3200/6993 [============>.................] - ETA: 0s - loss: 0.0518 - accuracy: 0.9894 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0571 - accuracy: 0.9897 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0625 - accuracy: 0.9893 4224/6993 [=================>............] - ETA: 0s - loss: 0.0596 - accuracy: 0.9893 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0556 - accuracy: 0.9897 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0583 - accuracy: 0.9889 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0649 - accuracy: 0.9880 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0630 - accuracy: 0.9883 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0604 - accuracy: 0.9887 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0600 - accuracy: 0.9890 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0614 - accuracy: 0.9890 6912/6993 [============================>.] - ETA: 0s - loss: 0.0594 - accuracy: 0.9894 6993/6993 [==============================] - 2s 233us/sample - loss: 0.0589 - accuracy: 0.9894 - val_loss: 0.8319 - val_accuracy: 0.9323 Evaluating model for iteration 3... 1019/1019 - 0s - loss: 0.6089 - accuracy: 0.9372 Accuracy for iteration 3 0.9371933341026306 Training model for iteration 4... Train on 6993 samples, validate on 1978 samples Epoch 1/199 128/6993 [..............................] - ETA: 22s - loss: 2.3705 - accuracy: 0.1328 896/6993 [==>...........................] - ETA: 3s - loss: 2.1847 - accuracy: 0.2042 1664/6993 [======>.......................] - ETA: 1s - loss: 2.0808 - accuracy: 0.2428 2432/6993 [=========>....................] - ETA: 1s - loss: 1.9901 - accuracy: 0.2701 3200/6993 [============>.................] - ETA: 0s - loss: 1.9375 - accuracy: 0.2919 4096/6993 [================>.............] - ETA: 0s - loss: 1.8758 - accuracy: 0.3147 4864/6993 [===================>..........] - ETA: 0s - loss: 1.8268 - accuracy: 0.3337 5632/6993 [=======================>......] - ETA: 0s - loss: 1.7826 - accuracy: 0.3514 6528/6993 [===========================>..] - ETA: 0s - loss: 1.7433 - accuracy: 0.3701 6993/6993 [==============================] - 2s 215us/sample - loss: 1.7240 - accuracy: 0.3794 - val_loss: 1.1710 - val_accuracy: 0.6016 Epoch 2/199 128/6993 [..............................] - ETA: 0s - loss: 1.3689 - accuracy: 0.5391 896/6993 [==>...........................] - ETA: 0s - loss: 1.3756 - accuracy: 0.5190 1536/6993 [=====>........................] - ETA: 0s - loss: 1.3797 - accuracy: 0.5124 2176/6993 [========>.....................] - ETA: 0s - loss: 1.3622 - accuracy: 0.5248 2816/6993 [===========>..................] - ETA: 0s - loss: 1.3391 - accuracy: 0.5376 3456/6993 [=============>................] - ETA: 0s - loss: 1.3195 - accuracy: 0.5486 4096/6993 [================>.............] - ETA: 0s - loss: 1.2972 - accuracy: 0.5569 4864/6993 [===================>..........] - ETA: 0s - loss: 1.2898 - accuracy: 0.5586 5632/6993 [=======================>......] - ETA: 0s - loss: 1.2732 - accuracy: 0.5641 6272/6993 [=========================>....] - ETA: 0s - loss: 1.2576 - accuracy: 0.5682 6656/6993 [===========================>..] - ETA: 0s - loss: 1.2454 - accuracy: 0.5738 6993/6993 [==============================] - 1s 98us/sample - loss: 1.2356 - accuracy: 0.5784 - val_loss: 0.9347 - val_accuracy: 0.6891 Epoch 3/199 128/6993 [..............................] - ETA: 0s - loss: 1.0318 - accuracy: 0.6250 896/6993 [==>...........................] - ETA: 0s - loss: 1.1362 - accuracy: 0.6217 1664/6993 [======>.......................] - ETA: 0s - loss: 1.0943 - accuracy: 0.6436 2432/6993 [=========>....................] - ETA: 0s - loss: 1.1004 - accuracy: 0.6283 3072/6993 [============>.................] - ETA: 0s - loss: 1.0871 - accuracy: 0.6338 3584/6993 [==============>...............] - ETA: 0s - loss: 1.0752 - accuracy: 0.6384 4096/6993 [================>.............] - ETA: 0s - loss: 1.0724 - accuracy: 0.6404 4608/6993 [==================>...........] - ETA: 0s - loss: 1.0641 - accuracy: 0.6447 5120/6993 [====================>.........] - ETA: 0s - loss: 1.0559 - accuracy: 0.6473 5760/6993 [=======================>......] - ETA: 0s - loss: 1.0379 - accuracy: 0.6536 6528/6993 [===========================>..] - ETA: 0s - loss: 1.0339 - accuracy: 0.6553 6993/6993 [==============================] - 1s 90us/sample - loss: 1.0311 - accuracy: 0.6572 - val_loss: 0.8032 - val_accuracy: 0.7310 Epoch 4/199 128/6993 [..............................] - ETA: 0s - loss: 0.9517 - accuracy: 0.6641 768/6993 [==>...........................] - ETA: 0s - loss: 0.9354 - accuracy: 0.6823 1408/6993 [=====>........................] - ETA: 0s - loss: 0.9299 - accuracy: 0.6832 2048/6993 [=======>......................] - ETA: 0s - loss: 0.9204 - accuracy: 0.6914 2688/6993 [==========>...................] - ETA: 0s - loss: 0.9256 - accuracy: 0.6931 3456/6993 [=============>................] - ETA: 0s - loss: 0.9077 - accuracy: 0.6982 4096/6993 [================>.............] - ETA: 0s - loss: 0.9031 - accuracy: 0.7019 4736/6993 [===================>..........] - ETA: 0s - loss: 0.8873 - accuracy: 0.7090 5376/6993 [======================>.......] - ETA: 0s - loss: 0.8845 - accuracy: 0.7091 6016/6993 [========================>.....] - ETA: 0s - loss: 0.8881 - accuracy: 0.7078 6912/6993 [============================>.] - ETA: 0s - loss: 0.8909 - accuracy: 0.7082 6993/6993 [==============================] - 1s 90us/sample - loss: 0.8893 - accuracy: 0.7091 - val_loss: 0.7184 - val_accuracy: 0.7573 Epoch 5/199 128/6993 [..............................] - ETA: 1s - loss: 0.6473 - accuracy: 0.7812 896/6993 [==>...........................] - ETA: 0s - loss: 0.7333 - accuracy: 0.7578 1792/6993 [======>.......................] - ETA: 0s - loss: 0.7953 - accuracy: 0.7394 2560/6993 [=========>....................] - ETA: 0s - loss: 0.7747 - accuracy: 0.7434 3328/6993 [=============>................] - ETA: 0s - loss: 0.7766 - accuracy: 0.7392 4096/6993 [================>.............] - ETA: 0s - loss: 0.7635 - accuracy: 0.7471 4992/6993 [====================>.........] - ETA: 0s - loss: 0.7767 - accuracy: 0.7442 5760/6993 [=======================>......] - ETA: 0s - loss: 0.7732 - accuracy: 0.7474 6272/6993 [=========================>....] - ETA: 0s - loss: 0.7709 - accuracy: 0.7494 6656/6993 [===========================>..] - ETA: 0s - loss: 0.7733 - accuracy: 0.7495 6993/6993 [==============================] - 1s 102us/sample - loss: 0.7758 - accuracy: 0.7480 - val_loss: 0.6831 - val_accuracy: 0.7806 Epoch 6/199 128/6993 [..............................] - ETA: 0s - loss: 0.5880 - accuracy: 0.8359 512/6993 [=>............................] - ETA: 0s - loss: 0.6897 - accuracy: 0.7988 896/6993 [==>...........................] - ETA: 0s - loss: 0.6767 - accuracy: 0.7958 1408/6993 [=====>........................] - ETA: 0s - loss: 0.6815 - accuracy: 0.7905 1920/6993 [=======>......................] - ETA: 0s - loss: 0.7034 - accuracy: 0.7786 2560/6993 [=========>....................] - ETA: 0s - loss: 0.7150 - accuracy: 0.7758 3072/6993 [============>.................] - ETA: 0s - loss: 0.7275 - accuracy: 0.7754 3840/6993 [===============>..............] - ETA: 0s - loss: 0.7329 - accuracy: 0.7740 4224/6993 [=================>............] - ETA: 0s - loss: 0.7298 - accuracy: 0.7741 4736/6993 [===================>..........] - ETA: 0s - loss: 0.7263 - accuracy: 0.7745 5376/6993 [======================>.......] - ETA: 0s - loss: 0.7217 - accuracy: 0.7755 6144/6993 [=========================>....] - ETA: 0s - loss: 0.7226 - accuracy: 0.7764 6993/6993 [==============================] - 1s 109us/sample - loss: 0.7153 - accuracy: 0.7768 - val_loss: 0.6750 - val_accuracy: 0.7735 Epoch 7/199 128/6993 [..............................] - ETA: 0s - loss: 0.5839 - accuracy: 0.8281 896/6993 [==>...........................] - ETA: 0s - loss: 0.6309 - accuracy: 0.8002 1792/6993 [======>.......................] - ETA: 0s - loss: 0.6400 - accuracy: 0.7930 2560/6993 [=========>....................] - ETA: 0s - loss: 0.6294 - accuracy: 0.7965 3072/6993 [============>.................] - ETA: 0s - loss: 0.6322 - accuracy: 0.7943 3712/6993 [==============>...............] - ETA: 0s - loss: 0.6450 - accuracy: 0.7912 4352/6993 [=================>............] - ETA: 0s - loss: 0.6444 - accuracy: 0.7941 5248/6993 [=====================>........] - ETA: 0s - loss: 0.6395 - accuracy: 0.7942 6016/6993 [========================>.....] - ETA: 0s - loss: 0.6295 - accuracy: 0.7982 6912/6993 [============================>.] - ETA: 0s - loss: 0.6372 - accuracy: 0.7983 6993/6993 [==============================] - 1s 83us/sample - loss: 0.6359 - accuracy: 0.7988 - val_loss: 0.5875 - val_accuracy: 0.7978 Epoch 8/199 128/6993 [..............................] - ETA: 0s - loss: 0.4615 - accuracy: 0.8594 896/6993 [==>...........................] - ETA: 0s - loss: 0.5289 - accuracy: 0.8359 1536/6993 [=====>........................] - ETA: 0s - loss: 0.5441 - accuracy: 0.8379 2432/6993 [=========>....................] - ETA: 0s - loss: 0.5502 - accuracy: 0.8306 3072/6993 [============>.................] - ETA: 0s - loss: 0.5570 - accuracy: 0.8275 3712/6993 [==============>...............] - ETA: 0s - loss: 0.5503 - accuracy: 0.8292 4224/6993 [=================>............] - ETA: 0s - loss: 0.5515 - accuracy: 0.8265 4608/6993 [==================>...........] - ETA: 0s - loss: 0.5543 - accuracy: 0.8236 5248/6993 [=====================>........] - ETA: 0s - loss: 0.5569 - accuracy: 0.8237 5888/6993 [========================>.....] - ETA: 0s - loss: 0.5640 - accuracy: 0.8220 6528/6993 [===========================>..] - ETA: 0s - loss: 0.5610 - accuracy: 0.8228 6993/6993 [==============================] - 1s 101us/sample - loss: 0.5628 - accuracy: 0.8228 - val_loss: 0.5765 - val_accuracy: 0.8150 Epoch 9/199 128/6993 [..............................] - ETA: 0s - loss: 0.4700 - accuracy: 0.8672 768/6993 [==>...........................] - ETA: 0s - loss: 0.4765 - accuracy: 0.8451 1408/6993 [=====>........................] - ETA: 0s - loss: 0.5246 - accuracy: 0.8338 2176/6993 [========>.....................] - ETA: 0s - loss: 0.5299 - accuracy: 0.8346 2816/6993 [===========>..................] - ETA: 0s - loss: 0.5228 - accuracy: 0.8324 3456/6993 [=============>................] - ETA: 0s - loss: 0.5317 - accuracy: 0.8302 4096/6993 [================>.............] - ETA: 0s - loss: 0.5296 - accuracy: 0.8318 4736/6993 [===================>..........] - ETA: 0s - loss: 0.5282 - accuracy: 0.8317 5376/6993 [======================>.......] - ETA: 0s - loss: 0.5282 - accuracy: 0.8318 6272/6993 [=========================>....] - ETA: 0s - loss: 0.5199 - accuracy: 0.8329 6993/6993 [==============================] - 1s 88us/sample - loss: 0.5237 - accuracy: 0.8337 - val_loss: 0.5158 - val_accuracy: 0.8372 Epoch 10/199 128/6993 [..............................] - ETA: 0s - loss: 0.4424 - accuracy: 0.8516 768/6993 [==>...........................] - ETA: 0s - loss: 0.4429 - accuracy: 0.8568 1536/6993 [=====>........................] - ETA: 0s - loss: 0.4899 - accuracy: 0.8418 2176/6993 [========>.....................] - ETA: 0s - loss: 0.5062 - accuracy: 0.8415 2944/6993 [===========>..................] - ETA: 0s - loss: 0.4943 - accuracy: 0.8458 3456/6993 [=============>................] - ETA: 0s - loss: 0.4987 - accuracy: 0.8449 4352/6993 [=================>............] - ETA: 0s - loss: 0.4898 - accuracy: 0.8493 5120/6993 [====================>.........] - ETA: 0s - loss: 0.4840 - accuracy: 0.8510 5760/6993 [=======================>......] - ETA: 0s - loss: 0.4784 - accuracy: 0.8512 6400/6993 [==========================>...] - ETA: 0s - loss: 0.4803 - accuracy: 0.8514 6993/6993 [==============================] - 1s 91us/sample - loss: 0.4800 - accuracy: 0.8519 - val_loss: 0.4990 - val_accuracy: 0.8377 Epoch 11/199 128/6993 [..............................] - ETA: 0s - loss: 0.4614 - accuracy: 0.8359 896/6993 [==>...........................] - ETA: 0s - loss: 0.3957 - accuracy: 0.8627 1664/6993 [======>.......................] - ETA: 0s - loss: 0.3987 - accuracy: 0.8750 2304/6993 [========>.....................] - ETA: 0s - loss: 0.4043 - accuracy: 0.8724 3072/6993 [============>.................] - ETA: 0s - loss: 0.4427 - accuracy: 0.8626 3840/6993 [===============>..............] - ETA: 0s - loss: 0.4416 - accuracy: 0.8648 4480/6993 [==================>...........] - ETA: 0s - loss: 0.4358 - accuracy: 0.8652 5248/6993 [=====================>........] - ETA: 0s - loss: 0.4377 - accuracy: 0.8653 5760/6993 [=======================>......] - ETA: 0s - loss: 0.4388 - accuracy: 0.8646 6400/6993 [==========================>...] - ETA: 0s - loss: 0.4431 - accuracy: 0.8628 6993/6993 [==============================] - 1s 87us/sample - loss: 0.4373 - accuracy: 0.8643 - val_loss: 0.4762 - val_accuracy: 0.8478 Epoch 12/199 128/6993 [..............................] - ETA: 0s - loss: 0.4819 - accuracy: 0.8594 896/6993 [==>...........................] - ETA: 0s - loss: 0.3760 - accuracy: 0.8862 1664/6993 [======>.......................] - ETA: 0s - loss: 0.3907 - accuracy: 0.8762 2304/6993 [========>.....................] - ETA: 0s - loss: 0.3810 - accuracy: 0.8759 2944/6993 [===========>..................] - ETA: 0s - loss: 0.3879 - accuracy: 0.8757 3712/6993 [==============>...............] - ETA: 0s - loss: 0.4010 - accuracy: 0.8726 4480/6993 [==================>...........] - ETA: 0s - loss: 0.4173 - accuracy: 0.8683 5120/6993 [====================>.........] - ETA: 0s - loss: 0.4127 - accuracy: 0.8707 5888/6993 [========================>.....] - ETA: 0s - loss: 0.4051 - accuracy: 0.8743 6528/6993 [===========================>..] - ETA: 0s - loss: 0.4016 - accuracy: 0.8752 6993/6993 [==============================] - 1s 88us/sample - loss: 0.3994 - accuracy: 0.8762 - val_loss: 0.5487 - val_accuracy: 0.8468 Epoch 13/199 128/6993 [..............................] - ETA: 1s - loss: 0.3686 - accuracy: 0.9062 768/6993 [==>...........................] - ETA: 0s - loss: 0.3807 - accuracy: 0.8906 1408/6993 [=====>........................] - ETA: 0s - loss: 0.3886 - accuracy: 0.8842 2048/6993 [=======>......................] - ETA: 0s - loss: 0.3855 - accuracy: 0.8857 2688/6993 [==========>...................] - ETA: 0s - loss: 0.3848 - accuracy: 0.8839 3328/6993 [=============>................] - ETA: 0s - loss: 0.3734 - accuracy: 0.8870 3968/6993 [================>.............] - ETA: 0s - loss: 0.3712 - accuracy: 0.8886 4608/6993 [==================>...........] - ETA: 0s - loss: 0.3778 - accuracy: 0.8837 5248/6993 [=====================>........] - ETA: 0s - loss: 0.3828 - accuracy: 0.8832 5888/6993 [========================>.....] - ETA: 0s - loss: 0.3799 - accuracy: 0.8830 6528/6993 [===========================>..] - ETA: 0s - loss: 0.3775 - accuracy: 0.8834 6993/6993 [==============================] - 1s 93us/sample - loss: 0.3734 - accuracy: 0.8855 - val_loss: 0.4518 - val_accuracy: 0.8660 Epoch 14/199 128/6993 [..............................] - ETA: 0s - loss: 0.2603 - accuracy: 0.9219 896/6993 [==>...........................] - ETA: 0s - loss: 0.3225 - accuracy: 0.9085 1536/6993 [=====>........................] - ETA: 0s - loss: 0.3187 - accuracy: 0.9062 2048/6993 [=======>......................] - ETA: 0s - loss: 0.3225 - accuracy: 0.9038 2688/6993 [==========>...................] - ETA: 0s - loss: 0.3212 - accuracy: 0.9044 3200/6993 [============>.................] - ETA: 0s - loss: 0.3371 - accuracy: 0.8984 3840/6993 [===============>..............] - ETA: 0s - loss: 0.3355 - accuracy: 0.8987 4224/6993 [=================>............] - ETA: 0s - loss: 0.3336 - accuracy: 0.9003 4736/6993 [===================>..........] - ETA: 0s - loss: 0.3338 - accuracy: 0.8999 5376/6993 [======================>.......] - ETA: 0s - loss: 0.3424 - accuracy: 0.8971 6016/6993 [========================>.....] - ETA: 0s - loss: 0.3374 - accuracy: 0.8981 6656/6993 [===========================>..] - ETA: 0s - loss: 0.3426 - accuracy: 0.8969 6993/6993 [==============================] - 1s 109us/sample - loss: 0.3442 - accuracy: 0.8963 - val_loss: 0.4175 - val_accuracy: 0.8696 Epoch 15/199 128/6993 [..............................] - ETA: 0s - loss: 0.3396 - accuracy: 0.8906 640/6993 [=>............................] - ETA: 0s - loss: 0.3256 - accuracy: 0.9031 1152/6993 [===>..........................] - ETA: 0s - loss: 0.3303 - accuracy: 0.9028 1664/6993 [======>.......................] - ETA: 0s - loss: 0.3177 - accuracy: 0.9062 2304/6993 [========>.....................] - ETA: 0s - loss: 0.3059 - accuracy: 0.9062 2944/6993 [===========>..................] - ETA: 0s - loss: 0.3100 - accuracy: 0.9049 3712/6993 [==============>...............] - ETA: 0s - loss: 0.3098 - accuracy: 0.9044 4480/6993 [==================>...........] - ETA: 0s - loss: 0.3149 - accuracy: 0.9031 5120/6993 [====================>.........] - ETA: 0s - loss: 0.3099 - accuracy: 0.9018 5888/6993 [========================>.....] - ETA: 0s - loss: 0.3180 - accuracy: 0.9015 6528/6993 [===========================>..] - ETA: 0s - loss: 0.3289 - accuracy: 0.8992 6993/6993 [==============================] - 1s 91us/sample - loss: 0.3295 - accuracy: 0.8995 - val_loss: 0.4596 - val_accuracy: 0.8650 Epoch 16/199 128/6993 [..............................] - ETA: 0s - loss: 0.2494 - accuracy: 0.9297 768/6993 [==>...........................] - ETA: 0s - loss: 0.2922 - accuracy: 0.9193 1408/6993 [=====>........................] - ETA: 0s - loss: 0.3237 - accuracy: 0.9020 1920/6993 [=======>......................] - ETA: 0s - loss: 0.2939 - accuracy: 0.9120 2560/6993 [=========>....................] - ETA: 0s - loss: 0.2795 - accuracy: 0.9156 3200/6993 [============>.................] - ETA: 0s - loss: 0.2796 - accuracy: 0.9169 3840/6993 [===============>..............] - ETA: 0s - loss: 0.2768 - accuracy: 0.9169 4608/6993 [==================>...........] - ETA: 0s - loss: 0.2867 - accuracy: 0.9123 5248/6993 [=====================>........] - ETA: 0s - loss: 0.2848 - accuracy: 0.9129 5760/6993 [=======================>......] - ETA: 0s - loss: 0.2903 - accuracy: 0.9109 6528/6993 [===========================>..] - ETA: 0s - loss: 0.2939 - accuracy: 0.9104 6993/6993 [==============================] - 1s 98us/sample - loss: 0.2955 - accuracy: 0.9098 - val_loss: 0.4370 - val_accuracy: 0.8680 Epoch 17/199 128/6993 [..............................] - ETA: 1s - loss: 0.3064 - accuracy: 0.8750 768/6993 [==>...........................] - ETA: 0s - loss: 0.2537 - accuracy: 0.9232 1408/6993 [=====>........................] - ETA: 0s - loss: 0.2702 - accuracy: 0.9169 1920/6993 [=======>......................] - ETA: 0s - loss: 0.2781 - accuracy: 0.9203 2688/6993 [==========>...................] - ETA: 0s - loss: 0.2761 - accuracy: 0.9182 3328/6993 [=============>................] - ETA: 0s - loss: 0.2762 - accuracy: 0.9174 3968/6993 [================>.............] - ETA: 0s - loss: 0.2688 - accuracy: 0.9194 4608/6993 [==================>...........] - ETA: 0s - loss: 0.2864 - accuracy: 0.9154 5248/6993 [=====================>........] - ETA: 0s - loss: 0.2870 - accuracy: 0.9152 5888/6993 [========================>.....] - ETA: 0s - loss: 0.2840 - accuracy: 0.9149 6528/6993 [===========================>..] - ETA: 0s - loss: 0.2845 - accuracy: 0.9150 6993/6993 [==============================] - 1s 93us/sample - loss: 0.2841 - accuracy: 0.9156 - val_loss: 0.4303 - val_accuracy: 0.8751 Epoch 18/199 128/6993 [..............................] - ETA: 0s - loss: 0.1867 - accuracy: 0.9219 640/6993 [=>............................] - ETA: 0s - loss: 0.2479 - accuracy: 0.9172 1280/6993 [====>.........................] - ETA: 0s - loss: 0.2278 - accuracy: 0.9266 2048/6993 [=======>......................] - ETA: 0s - loss: 0.2352 - accuracy: 0.9248 2816/6993 [===========>..................] - ETA: 0s - loss: 0.2422 - accuracy: 0.9212 3584/6993 [==============>...............] - ETA: 0s - loss: 0.2414 - accuracy: 0.9230 4352/6993 [=================>............] - ETA: 0s - loss: 0.2468 - accuracy: 0.9233 5120/6993 [====================>.........] - ETA: 0s - loss: 0.2476 - accuracy: 0.9252 5888/6993 [========================>.....] - ETA: 0s - loss: 0.2503 - accuracy: 0.9246 6528/6993 [===========================>..] - ETA: 0s - loss: 0.2547 - accuracy: 0.9233 6993/6993 [==============================] - 1s 89us/sample - loss: 0.2607 - accuracy: 0.9222 - val_loss: 0.4224 - val_accuracy: 0.8857 Epoch 19/199 128/6993 [..............................] - ETA: 0s - loss: 0.2660 - accuracy: 0.8828 768/6993 [==>...........................] - ETA: 0s - loss: 0.2799 - accuracy: 0.9128 1408/6993 [=====>........................] - ETA: 0s - loss: 0.2320 - accuracy: 0.9339 2048/6993 [=======>......................] - ETA: 0s - loss: 0.2400 - accuracy: 0.9326 2688/6993 [==========>...................] - ETA: 0s - loss: 0.2223 - accuracy: 0.9338 3200/6993 [============>.................] - ETA: 0s - loss: 0.2153 - accuracy: 0.9344 3840/6993 [===============>..............] - ETA: 0s - loss: 0.2165 - accuracy: 0.9318 4480/6993 [==================>...........] - ETA: 0s - loss: 0.2131 - accuracy: 0.9319 4992/6993 [====================>.........] - ETA: 0s - loss: 0.2203 - accuracy: 0.9299 5632/6993 [=======================>......] - ETA: 0s - loss: 0.2287 - accuracy: 0.9292 6272/6993 [=========================>....] - ETA: 0s - loss: 0.2309 - accuracy: 0.9276 6912/6993 [============================>.] - ETA: 0s - loss: 0.2347 - accuracy: 0.9265 6993/6993 [==============================] - 1s 96us/sample - loss: 0.2359 - accuracy: 0.9262 - val_loss: 0.4160 - val_accuracy: 0.8817 Epoch 20/199 128/6993 [..............................] - ETA: 0s - loss: 0.3053 - accuracy: 0.9219 768/6993 [==>...........................] - ETA: 0s - loss: 0.2172 - accuracy: 0.9349 1408/6993 [=====>........................] - ETA: 0s - loss: 0.2337 - accuracy: 0.9290 2048/6993 [=======>......................] - ETA: 0s - loss: 0.2534 - accuracy: 0.9248 2816/6993 [===========>..................] - ETA: 0s - loss: 0.2468 - accuracy: 0.9247 3584/6993 [==============>...............] - ETA: 0s - loss: 0.2450 - accuracy: 0.9261 4352/6993 [=================>............] - ETA: 0s - loss: 0.2332 - accuracy: 0.9295 5120/6993 [====================>.........] - ETA: 0s - loss: 0.2414 - accuracy: 0.9275 5888/6993 [========================>.....] - ETA: 0s - loss: 0.2435 - accuracy: 0.9265 6528/6993 [===========================>..] - ETA: 0s - loss: 0.2458 - accuracy: 0.9262 6993/6993 [==============================] - 1s 87us/sample - loss: 0.2448 - accuracy: 0.9262 - val_loss: 0.3841 - val_accuracy: 0.8857 Epoch 21/199 128/6993 [..............................] - ETA: 0s - loss: 0.0525 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.2035 - accuracy: 0.9408 1664/6993 [======>.......................] - ETA: 0s - loss: 0.2070 - accuracy: 0.9345 2560/6993 [=========>....................] - ETA: 0s - loss: 0.2058 - accuracy: 0.9348 3200/6993 [============>.................] - ETA: 0s - loss: 0.2078 - accuracy: 0.9366 3840/6993 [===============>..............] - ETA: 0s - loss: 0.2059 - accuracy: 0.9372 4608/6993 [==================>...........] - ETA: 0s - loss: 0.2009 - accuracy: 0.9390 5504/6993 [======================>.......] - ETA: 0s - loss: 0.2066 - accuracy: 0.9379 6272/6993 [=========================>....] - ETA: 0s - loss: 0.2076 - accuracy: 0.9377 6993/6993 [==============================] - 1s 83us/sample - loss: 0.2023 - accuracy: 0.9382 - val_loss: 0.5646 - val_accuracy: 0.8610 Epoch 22/199 128/6993 [..............................] - ETA: 0s - loss: 0.5485 - accuracy: 0.8672 768/6993 [==>...........................] - ETA: 0s - loss: 0.3346 - accuracy: 0.9141 1664/6993 [======>.......................] - ETA: 0s - loss: 0.2747 - accuracy: 0.9177 2432/6993 [=========>....................] - ETA: 0s - loss: 0.2520 - accuracy: 0.9280 3328/6993 [=============>................] - ETA: 0s - loss: 0.2378 - accuracy: 0.9315 3968/6993 [================>.............] - ETA: 0s - loss: 0.2293 - accuracy: 0.9352 4480/6993 [==================>...........] - ETA: 0s - loss: 0.2317 - accuracy: 0.9339 5120/6993 [====================>.........] - ETA: 0s - loss: 0.2257 - accuracy: 0.9359 5632/6993 [=======================>......] - ETA: 0s - loss: 0.2183 - accuracy: 0.9368 6144/6993 [=========================>....] - ETA: 0s - loss: 0.2194 - accuracy: 0.9360 6784/6993 [============================>.] - ETA: 0s - loss: 0.2246 - accuracy: 0.9343 6993/6993 [==============================] - 1s 103us/sample - loss: 0.2261 - accuracy: 0.9338 - val_loss: 0.3973 - val_accuracy: 0.8923 Epoch 23/199 128/6993 [..............................] - ETA: 0s - loss: 0.0679 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1988 - accuracy: 0.9442 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1802 - accuracy: 0.9442 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1855 - accuracy: 0.9406 3456/6993 [=============>................] - ETA: 0s - loss: 0.1975 - accuracy: 0.9387 4224/6993 [=================>............] - ETA: 0s - loss: 0.1940 - accuracy: 0.9411 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1888 - accuracy: 0.9435 5888/6993 [========================>.....] - ETA: 0s - loss: 0.1954 - accuracy: 0.9407 6528/6993 [===========================>..] - ETA: 0s - loss: 0.2019 - accuracy: 0.9393 6993/6993 [==============================] - 1s 87us/sample - loss: 0.2003 - accuracy: 0.9401 - val_loss: 0.3874 - val_accuracy: 0.8999 Epoch 24/199 128/6993 [..............................] - ETA: 0s - loss: 0.3441 - accuracy: 0.9531 896/6993 [==>...........................] - ETA: 0s - loss: 0.2186 - accuracy: 0.9442 1664/6993 [======>.......................] - ETA: 0s - loss: 0.2267 - accuracy: 0.9423 2432/6993 [=========>....................] - ETA: 0s - loss: 0.2111 - accuracy: 0.9428 3328/6993 [=============>................] - ETA: 0s - loss: 0.2094 - accuracy: 0.9423 4096/6993 [================>.............] - ETA: 0s - loss: 0.2099 - accuracy: 0.9409 4736/6993 [===================>..........] - ETA: 0s - loss: 0.2077 - accuracy: 0.9398 5632/6993 [=======================>......] - ETA: 0s - loss: 0.2058 - accuracy: 0.9409 6400/6993 [==========================>...] - ETA: 0s - loss: 0.2079 - accuracy: 0.9403 6993/6993 [==============================] - 1s 84us/sample - loss: 0.2017 - accuracy: 0.9411 - val_loss: 0.4212 - val_accuracy: 0.8933 Epoch 25/199 128/6993 [..............................] - ETA: 0s - loss: 0.1620 - accuracy: 0.9531 1024/6993 [===>..........................] - ETA: 0s - loss: 0.1469 - accuracy: 0.9531 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1604 - accuracy: 0.9509 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1678 - accuracy: 0.9504 3200/6993 [============>.................] - ETA: 0s - loss: 0.1759 - accuracy: 0.9494 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1818 - accuracy: 0.9474 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1796 - accuracy: 0.9480 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1750 - accuracy: 0.9492 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1785 - accuracy: 0.9476 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1776 - accuracy: 0.9483 6993/6993 [==============================] - 1s 95us/sample - loss: 0.1768 - accuracy: 0.9491 - val_loss: 0.3840 - val_accuracy: 0.9070 Epoch 26/199 128/6993 [..............................] - ETA: 0s - loss: 0.1505 - accuracy: 0.9609 768/6993 [==>...........................] - ETA: 0s - loss: 0.1783 - accuracy: 0.9427 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1972 - accuracy: 0.9440 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1929 - accuracy: 0.9449 3200/6993 [============>.................] - ETA: 0s - loss: 0.1834 - accuracy: 0.9475 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1817 - accuracy: 0.9477 4352/6993 [=================>............] - ETA: 0s - loss: 0.1817 - accuracy: 0.9476 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1842 - accuracy: 0.9479 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1873 - accuracy: 0.9479 6400/6993 [==========================>...] - ETA: 0s - loss: 0.1902 - accuracy: 0.9469 6993/6993 [==============================] - 1s 95us/sample - loss: 0.1897 - accuracy: 0.9468 - val_loss: 0.4027 - val_accuracy: 0.8953 Epoch 27/199 128/6993 [..............................] - ETA: 0s - loss: 0.0618 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.1393 - accuracy: 0.9557 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1527 - accuracy: 0.9544 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1582 - accuracy: 0.9536 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1701 - accuracy: 0.9501 3200/6993 [============>.................] - ETA: 0s - loss: 0.1721 - accuracy: 0.9484 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1653 - accuracy: 0.9497 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1734 - accuracy: 0.9482 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1731 - accuracy: 0.9482 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1698 - accuracy: 0.9490 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1746 - accuracy: 0.9482 6993/6993 [==============================] - 1s 96us/sample - loss: 0.1776 - accuracy: 0.9481 - val_loss: 0.3811 - val_accuracy: 0.9024 Epoch 28/199 128/6993 [..............................] - ETA: 0s - loss: 0.2390 - accuracy: 0.9297 896/6993 [==>...........................] - ETA: 0s - loss: 0.1687 - accuracy: 0.9509 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1557 - accuracy: 0.9567 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1450 - accuracy: 0.9578 3328/6993 [=============>................] - ETA: 0s - loss: 0.1474 - accuracy: 0.9561 4096/6993 [================>.............] - ETA: 0s - loss: 0.1480 - accuracy: 0.9558 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1547 - accuracy: 0.9550 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1565 - accuracy: 0.9547 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1632 - accuracy: 0.9522 6993/6993 [==============================] - 1s 84us/sample - loss: 0.1680 - accuracy: 0.9508 - val_loss: 0.4142 - val_accuracy: 0.9039 Epoch 29/199 128/6993 [..............................] - ETA: 0s - loss: 0.1822 - accuracy: 0.9531 768/6993 [==>...........................] - ETA: 0s - loss: 0.1255 - accuracy: 0.9688 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1355 - accuracy: 0.9622 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1451 - accuracy: 0.9614 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1404 - accuracy: 0.9623 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1431 - accuracy: 0.9607 4352/6993 [=================>............] - ETA: 0s - loss: 0.1438 - accuracy: 0.9602 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1425 - accuracy: 0.9607 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1458 - accuracy: 0.9590 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1455 - accuracy: 0.9585 6784/6993 [============================>.] - ETA: 0s - loss: 0.1492 - accuracy: 0.9580 6993/6993 [==============================] - 1s 93us/sample - loss: 0.1514 - accuracy: 0.9564 - val_loss: 0.3914 - val_accuracy: 0.8959 Epoch 30/199 128/6993 [..............................] - ETA: 0s - loss: 0.1259 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.1156 - accuracy: 0.9622 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1376 - accuracy: 0.9616 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1598 - accuracy: 0.9552 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1553 - accuracy: 0.9569 3456/6993 [=============>................] - ETA: 0s - loss: 0.1608 - accuracy: 0.9572 3968/6993 [================>.............] - ETA: 0s - loss: 0.1547 - accuracy: 0.9584 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1533 - accuracy: 0.9588 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1543 - accuracy: 0.9574 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1573 - accuracy: 0.9576 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1638 - accuracy: 0.9554 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1615 - accuracy: 0.9554 6912/6993 [============================>.] - ETA: 0s - loss: 0.1597 - accuracy: 0.9562 6993/6993 [==============================] - 1s 117us/sample - loss: 0.1597 - accuracy: 0.9560 - val_loss: 0.3714 - val_accuracy: 0.9080 Epoch 31/199 128/6993 [..............................] - ETA: 0s - loss: 0.1940 - accuracy: 0.9609 640/6993 [=>............................] - ETA: 0s - loss: 0.1087 - accuracy: 0.9719 1152/6993 [===>..........................] - ETA: 0s - loss: 0.1302 - accuracy: 0.9618 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1177 - accuracy: 0.9651 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1191 - accuracy: 0.9665 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1233 - accuracy: 0.9637 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1385 - accuracy: 0.9599 3456/6993 [=============>................] - ETA: 0s - loss: 0.1438 - accuracy: 0.9598 3968/6993 [================>.............] - ETA: 0s - loss: 0.1424 - accuracy: 0.9604 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1439 - accuracy: 0.9594 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1492 - accuracy: 0.9577 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1494 - accuracy: 0.9581 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1523 - accuracy: 0.9570 6784/6993 [============================>.] - ETA: 0s - loss: 0.1509 - accuracy: 0.9575 6993/6993 [==============================] - 1s 126us/sample - loss: 0.1504 - accuracy: 0.9574 - val_loss: 0.3741 - val_accuracy: 0.9055 Epoch 32/199 128/6993 [..............................] - ETA: 0s - loss: 0.1053 - accuracy: 0.9609 768/6993 [==>...........................] - ETA: 0s - loss: 0.1146 - accuracy: 0.9648 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1605 - accuracy: 0.9560 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1567 - accuracy: 0.9546 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1543 - accuracy: 0.9546 3328/6993 [=============>................] - ETA: 0s - loss: 0.1424 - accuracy: 0.9576 4096/6993 [================>.............] - ETA: 0s - loss: 0.1383 - accuracy: 0.9587 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1403 - accuracy: 0.9590 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1406 - accuracy: 0.9583 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1495 - accuracy: 0.9576 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1483 - accuracy: 0.9576 6993/6993 [==============================] - 1s 94us/sample - loss: 0.1473 - accuracy: 0.9575 - val_loss: 0.4186 - val_accuracy: 0.9004 Epoch 33/199 128/6993 [..............................] - ETA: 0s - loss: 0.1148 - accuracy: 0.9531 768/6993 [==>...........................] - ETA: 0s - loss: 0.1087 - accuracy: 0.9635 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1311 - accuracy: 0.9624 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1164 - accuracy: 0.9658 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1219 - accuracy: 0.9643 3456/6993 [=============>................] - ETA: 0s - loss: 0.1283 - accuracy: 0.9621 4096/6993 [================>.............] - ETA: 0s - loss: 0.1311 - accuracy: 0.9622 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1335 - accuracy: 0.9618 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1327 - accuracy: 0.9619 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1406 - accuracy: 0.9603 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1419 - accuracy: 0.9606 6993/6993 [==============================] - 1s 91us/sample - loss: 0.1413 - accuracy: 0.9602 - val_loss: 0.3822 - val_accuracy: 0.9024 Epoch 34/199 128/6993 [..............................] - ETA: 0s - loss: 0.0693 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1005 - accuracy: 0.9727 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1155 - accuracy: 0.9664 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1037 - accuracy: 0.9688 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1181 - accuracy: 0.9668 3200/6993 [============>.................] - ETA: 0s - loss: 0.1199 - accuracy: 0.9653 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1139 - accuracy: 0.9672 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1309 - accuracy: 0.9652 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1364 - accuracy: 0.9629 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1355 - accuracy: 0.9639 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1363 - accuracy: 0.9643 6993/6993 [==============================] - 1s 95us/sample - loss: 0.1390 - accuracy: 0.9632 - val_loss: 0.3595 - val_accuracy: 0.9115 Epoch 35/199 128/6993 [..............................] - ETA: 0s - loss: 0.0892 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.1108 - accuracy: 0.9661 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1335 - accuracy: 0.9645 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1272 - accuracy: 0.9644 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1161 - accuracy: 0.9669 3456/6993 [=============>................] - ETA: 0s - loss: 0.1241 - accuracy: 0.9656 4096/6993 [================>.............] - ETA: 0s - loss: 0.1221 - accuracy: 0.9648 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1197 - accuracy: 0.9655 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1236 - accuracy: 0.9645 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1243 - accuracy: 0.9636 6993/6993 [==============================] - 1s 92us/sample - loss: 0.1259 - accuracy: 0.9631 - val_loss: 0.4004 - val_accuracy: 0.9090 Epoch 36/199 128/6993 [..............................] - ETA: 0s - loss: 0.1846 - accuracy: 0.9531 896/6993 [==>...........................] - ETA: 0s - loss: 0.1518 - accuracy: 0.9587 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1375 - accuracy: 0.9609 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1250 - accuracy: 0.9640 3200/6993 [============>.................] - ETA: 0s - loss: 0.1226 - accuracy: 0.9650 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1201 - accuracy: 0.9656 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1291 - accuracy: 0.9650 5120/6993 [====================>.........] - ETA: 0s - loss: 0.1341 - accuracy: 0.9633 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1349 - accuracy: 0.9628 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1355 - accuracy: 0.9628 6993/6993 [==============================] - 1s 84us/sample - loss: 0.1363 - accuracy: 0.9630 - val_loss: 0.4043 - val_accuracy: 0.9120 Epoch 37/199 128/6993 [..............................] - ETA: 0s - loss: 0.0701 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.1145 - accuracy: 0.9743 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1104 - accuracy: 0.9740 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0994 - accuracy: 0.9757 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1080 - accuracy: 0.9721 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1128 - accuracy: 0.9682 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1111 - accuracy: 0.9681 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1166 - accuracy: 0.9656 6016/6993 [========================>.....] - ETA: 0s - loss: 0.1155 - accuracy: 0.9658 6784/6993 [============================>.] - ETA: 0s - loss: 0.1214 - accuracy: 0.9651 6993/6993 [==============================] - 1s 83us/sample - loss: 0.1217 - accuracy: 0.9647 - val_loss: 0.4052 - val_accuracy: 0.9060 Epoch 38/199 128/6993 [..............................] - ETA: 0s - loss: 0.0419 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0780 - accuracy: 0.9754 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1119 - accuracy: 0.9669 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0970 - accuracy: 0.9705 3072/6993 [============>.................] - ETA: 0s - loss: 0.0951 - accuracy: 0.9704 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0968 - accuracy: 0.9709 4352/6993 [=================>............] - ETA: 0s - loss: 0.0959 - accuracy: 0.9704 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0990 - accuracy: 0.9700 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1020 - accuracy: 0.9691 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1146 - accuracy: 0.9678 6912/6993 [============================>.] - ETA: 0s - loss: 0.1176 - accuracy: 0.9677 6993/6993 [==============================] - 1s 92us/sample - loss: 0.1183 - accuracy: 0.9673 - val_loss: 0.4053 - val_accuracy: 0.9120 Epoch 39/199 128/6993 [..............................] - ETA: 0s - loss: 0.0917 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.0883 - accuracy: 0.9734 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0861 - accuracy: 0.9722 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1149 - accuracy: 0.9651 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1110 - accuracy: 0.9678 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1125 - accuracy: 0.9684 3200/6993 [============>.................] - ETA: 0s - loss: 0.1132 - accuracy: 0.9672 3712/6993 [==============>...............] - ETA: 0s - loss: 0.1253 - accuracy: 0.9661 4352/6993 [=================>............] - ETA: 0s - loss: 0.1351 - accuracy: 0.9637 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1318 - accuracy: 0.9647 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1296 - accuracy: 0.9652 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1272 - accuracy: 0.9654 6993/6993 [==============================] - 1s 105us/sample - loss: 0.1262 - accuracy: 0.9655 - val_loss: 0.3979 - val_accuracy: 0.9085 Epoch 40/199 128/6993 [..............................] - ETA: 1s - loss: 0.2910 - accuracy: 0.9453 768/6993 [==>...........................] - ETA: 0s - loss: 0.1373 - accuracy: 0.9701 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1188 - accuracy: 0.9723 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1145 - accuracy: 0.9702 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1095 - accuracy: 0.9714 3456/6993 [=============>................] - ETA: 0s - loss: 0.1109 - accuracy: 0.9714 4096/6993 [================>.............] - ETA: 0s - loss: 0.1157 - accuracy: 0.9705 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1174 - accuracy: 0.9694 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1161 - accuracy: 0.9695 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1224 - accuracy: 0.9683 6993/6993 [==============================] - 1s 90us/sample - loss: 0.1230 - accuracy: 0.9684 - val_loss: 0.3738 - val_accuracy: 0.9130 Epoch 41/199 128/6993 [..............................] - ETA: 0s - loss: 0.0492 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0849 - accuracy: 0.9777 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0953 - accuracy: 0.9754 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0938 - accuracy: 0.9762 3072/6993 [============>.................] - ETA: 0s - loss: 0.0960 - accuracy: 0.9736 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0975 - accuracy: 0.9728 4352/6993 [=================>............] - ETA: 0s - loss: 0.0984 - accuracy: 0.9717 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1048 - accuracy: 0.9698 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1050 - accuracy: 0.9703 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1105 - accuracy: 0.9689 6912/6993 [============================>.] - ETA: 0s - loss: 0.1105 - accuracy: 0.9693 6993/6993 [==============================] - 1s 94us/sample - loss: 0.1102 - accuracy: 0.9695 - val_loss: 0.3790 - val_accuracy: 0.9125 Epoch 42/199 128/6993 [..............................] - ETA: 0s - loss: 0.0412 - accuracy: 0.9844 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0771 - accuracy: 0.9785 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0762 - accuracy: 0.9808 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0819 - accuracy: 0.9762 3328/6993 [=============>................] - ETA: 0s - loss: 0.0895 - accuracy: 0.9739 3968/6993 [================>.............] - ETA: 0s - loss: 0.0959 - accuracy: 0.9725 4736/6993 [===================>..........] - ETA: 0s - loss: 0.1072 - accuracy: 0.9698 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1046 - accuracy: 0.9711 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1041 - accuracy: 0.9718 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1032 - accuracy: 0.9719 6993/6993 [==============================] - 1s 93us/sample - loss: 0.1029 - accuracy: 0.9720 - val_loss: 0.4114 - val_accuracy: 0.9176 Epoch 43/199 128/6993 [..............................] - ETA: 0s - loss: 0.0952 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0951 - accuracy: 0.9676 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1097 - accuracy: 0.9688 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0941 - accuracy: 0.9731 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0948 - accuracy: 0.9725 3456/6993 [=============>................] - ETA: 0s - loss: 0.0920 - accuracy: 0.9719 4096/6993 [================>.............] - ETA: 0s - loss: 0.0932 - accuracy: 0.9734 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0969 - accuracy: 0.9722 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0990 - accuracy: 0.9716 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1063 - accuracy: 0.9702 6784/6993 [============================>.] - ETA: 0s - loss: 0.1067 - accuracy: 0.9698 6993/6993 [==============================] - 1s 97us/sample - loss: 0.1111 - accuracy: 0.9694 - val_loss: 0.4435 - val_accuracy: 0.9141 Epoch 44/199 128/6993 [..............................] - ETA: 0s - loss: 0.0974 - accuracy: 0.9609 768/6993 [==>...........................] - ETA: 0s - loss: 0.0996 - accuracy: 0.9635 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0916 - accuracy: 0.9673 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0894 - accuracy: 0.9688 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1038 - accuracy: 0.9658 3456/6993 [=============>................] - ETA: 0s - loss: 0.1070 - accuracy: 0.9685 4096/6993 [================>.............] - ETA: 0s - loss: 0.1099 - accuracy: 0.9670 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1124 - accuracy: 0.9659 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1044 - accuracy: 0.9686 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1049 - accuracy: 0.9691 6993/6993 [==============================] - 1s 91us/sample - loss: 0.1044 - accuracy: 0.9697 - val_loss: 0.4284 - val_accuracy: 0.9125 Epoch 45/199 128/6993 [..............................] - ETA: 0s - loss: 0.0202 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1375 - accuracy: 0.9710 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1175 - accuracy: 0.9718 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1096 - accuracy: 0.9706 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1078 - accuracy: 0.9716 3456/6993 [=============>................] - ETA: 0s - loss: 0.1194 - accuracy: 0.9719 4096/6993 [================>.............] - ETA: 0s - loss: 0.1161 - accuracy: 0.9727 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1101 - accuracy: 0.9735 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1080 - accuracy: 0.9729 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1023 - accuracy: 0.9741 6912/6993 [============================>.] - ETA: 0s - loss: 0.0999 - accuracy: 0.9737 6993/6993 [==============================] - 1s 91us/sample - loss: 0.1009 - accuracy: 0.9733 - val_loss: 0.4371 - val_accuracy: 0.9141 Epoch 46/199 128/6993 [..............................] - ETA: 0s - loss: 0.0786 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0749 - accuracy: 0.9777 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1108 - accuracy: 0.9669 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1154 - accuracy: 0.9672 3328/6993 [=============>................] - ETA: 0s - loss: 0.1027 - accuracy: 0.9700 4096/6993 [================>.............] - ETA: 0s - loss: 0.1029 - accuracy: 0.9700 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1013 - accuracy: 0.9702 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0980 - accuracy: 0.9707 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0992 - accuracy: 0.9708 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0990 - accuracy: 0.9705 - val_loss: 0.4239 - val_accuracy: 0.9161 Epoch 47/199 128/6993 [..............................] - ETA: 0s - loss: 0.1875 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1082 - accuracy: 0.9766 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1043 - accuracy: 0.9746 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0940 - accuracy: 0.9761 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0956 - accuracy: 0.9744 3328/6993 [=============>................] - ETA: 0s - loss: 0.0962 - accuracy: 0.9742 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0990 - accuracy: 0.9732 4480/6993 [==================>...........] - ETA: 0s - loss: 0.1045 - accuracy: 0.9714 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1104 - accuracy: 0.9708 5376/6993 [======================>.......] - ETA: 0s - loss: 0.1081 - accuracy: 0.9714 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1043 - accuracy: 0.9720 6144/6993 [=========================>....] - ETA: 0s - loss: 0.1028 - accuracy: 0.9722 6528/6993 [===========================>..] - ETA: 0s - loss: 0.1033 - accuracy: 0.9720 6993/6993 [==============================] - 1s 113us/sample - loss: 0.1061 - accuracy: 0.9717 - val_loss: 0.4636 - val_accuracy: 0.9024 Epoch 48/199 128/6993 [..............................] - ETA: 0s - loss: 0.0543 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.0867 - accuracy: 0.9656 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1002 - accuracy: 0.9703 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0931 - accuracy: 0.9724 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0951 - accuracy: 0.9730 3200/6993 [============>.................] - ETA: 0s - loss: 0.1045 - accuracy: 0.9722 3840/6993 [===============>..............] - ETA: 0s - loss: 0.1025 - accuracy: 0.9742 4608/6993 [==================>...........] - ETA: 0s - loss: 0.1029 - accuracy: 0.9731 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1023 - accuracy: 0.9724 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1047 - accuracy: 0.9721 6993/6993 [==============================] - 1s 89us/sample - loss: 0.1086 - accuracy: 0.9720 - val_loss: 0.3939 - val_accuracy: 0.9146 Epoch 49/199 128/6993 [..............................] - ETA: 0s - loss: 0.0313 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0772 - accuracy: 0.9740 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1038 - accuracy: 0.9744 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0973 - accuracy: 0.9745 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0963 - accuracy: 0.9731 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0919 - accuracy: 0.9759 3456/6993 [=============>................] - ETA: 0s - loss: 0.0847 - accuracy: 0.9783 4224/6993 [=================>............] - ETA: 0s - loss: 0.0865 - accuracy: 0.9777 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0907 - accuracy: 0.9764 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0943 - accuracy: 0.9760 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0961 - accuracy: 0.9749 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0952 - accuracy: 0.9747 6912/6993 [============================>.] - ETA: 0s - loss: 0.0961 - accuracy: 0.9750 6993/6993 [==============================] - 1s 114us/sample - loss: 0.0957 - accuracy: 0.9748 - val_loss: 0.4284 - val_accuracy: 0.9130 Epoch 50/199 128/6993 [..............................] - ETA: 0s - loss: 0.0457 - accuracy: 0.9844 512/6993 [=>............................] - ETA: 0s - loss: 0.0649 - accuracy: 0.9805 896/6993 [==>...........................] - ETA: 0s - loss: 0.0582 - accuracy: 0.9833 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0585 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0583 - accuracy: 0.9833 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0647 - accuracy: 0.9826 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0696 - accuracy: 0.9812 3328/6993 [=============>................] - ETA: 0s - loss: 0.0741 - accuracy: 0.9814 3968/6993 [================>.............] - ETA: 0s - loss: 0.0771 - accuracy: 0.9811 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0815 - accuracy: 0.9796 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0811 - accuracy: 0.9792 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0859 - accuracy: 0.9784 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0947 - accuracy: 0.9772 6993/6993 [==============================] - 1s 124us/sample - loss: 0.0982 - accuracy: 0.9758 - val_loss: 0.4359 - val_accuracy: 0.9166 Epoch 51/199 128/6993 [..............................] - ETA: 0s - loss: 0.1407 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.0997 - accuracy: 0.9734 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0865 - accuracy: 0.9766 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0852 - accuracy: 0.9766 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0834 - accuracy: 0.9766 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0847 - accuracy: 0.9762 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0907 - accuracy: 0.9752 3968/6993 [================>.............] - ETA: 0s - loss: 0.0992 - accuracy: 0.9740 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0960 - accuracy: 0.9746 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0945 - accuracy: 0.9760 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0907 - accuracy: 0.9767 6784/6993 [============================>.] - ETA: 0s - loss: 0.0898 - accuracy: 0.9769 6993/6993 [==============================] - 1s 104us/sample - loss: 0.0909 - accuracy: 0.9761 - val_loss: 0.4253 - val_accuracy: 0.9141 Epoch 52/199 128/6993 [..............................] - ETA: 0s - loss: 0.0803 - accuracy: 0.9609 640/6993 [=>............................] - ETA: 0s - loss: 0.0519 - accuracy: 0.9812 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0643 - accuracy: 0.9781 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0776 - accuracy: 0.9805 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0964 - accuracy: 0.9758 3200/6993 [============>.................] - ETA: 0s - loss: 0.0899 - accuracy: 0.9775 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0855 - accuracy: 0.9776 4224/6993 [=================>............] - ETA: 0s - loss: 0.0892 - accuracy: 0.9768 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0895 - accuracy: 0.9778 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0854 - accuracy: 0.9792 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0813 - accuracy: 0.9801 6912/6993 [============================>.] - ETA: 0s - loss: 0.0813 - accuracy: 0.9800 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0814 - accuracy: 0.9798 - val_loss: 0.4772 - val_accuracy: 0.9181 Epoch 53/199 128/6993 [..............................] - ETA: 0s - loss: 0.0171 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0779 - accuracy: 0.9779 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1103 - accuracy: 0.9766 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1062 - accuracy: 0.9775 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0971 - accuracy: 0.9784 3328/6993 [=============>................] - ETA: 0s - loss: 0.0881 - accuracy: 0.9799 4096/6993 [================>.............] - ETA: 0s - loss: 0.0903 - accuracy: 0.9792 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0924 - accuracy: 0.9789 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0846 - accuracy: 0.9807 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0874 - accuracy: 0.9793 6912/6993 [============================>.] - ETA: 0s - loss: 0.0854 - accuracy: 0.9790 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0846 - accuracy: 0.9793 - val_loss: 0.4654 - val_accuracy: 0.9211 Epoch 54/199 128/6993 [..............................] - ETA: 0s - loss: 0.0681 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.1010 - accuracy: 0.9753 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0975 - accuracy: 0.9779 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1069 - accuracy: 0.9766 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1010 - accuracy: 0.9762 3456/6993 [=============>................] - ETA: 0s - loss: 0.1060 - accuracy: 0.9751 3968/6993 [================>.............] - ETA: 0s - loss: 0.1027 - accuracy: 0.9753 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0986 - accuracy: 0.9753 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0980 - accuracy: 0.9747 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0921 - accuracy: 0.9764 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0920 - accuracy: 0.9766 6993/6993 [==============================] - 1s 103us/sample - loss: 0.0912 - accuracy: 0.9770 - val_loss: 0.4391 - val_accuracy: 0.9110 Epoch 55/199 128/6993 [..............................] - ETA: 0s - loss: 0.1093 - accuracy: 0.9609 512/6993 [=>............................] - ETA: 0s - loss: 0.0773 - accuracy: 0.9785 896/6993 [==>...........................] - ETA: 0s - loss: 0.0819 - accuracy: 0.9788 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0741 - accuracy: 0.9797 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0959 - accuracy: 0.9760 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0991 - accuracy: 0.9729 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0923 - accuracy: 0.9743 3328/6993 [=============>................] - ETA: 0s - loss: 0.0923 - accuracy: 0.9742 3968/6993 [================>.............] - ETA: 0s - loss: 0.0899 - accuracy: 0.9735 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0952 - accuracy: 0.9737 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0932 - accuracy: 0.9739 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0913 - accuracy: 0.9733 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0955 - accuracy: 0.9730 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0973 - accuracy: 0.9729 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0985 - accuracy: 0.9732 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0981 - accuracy: 0.9734 6993/6993 [==============================] - 1s 151us/sample - loss: 0.1003 - accuracy: 0.9727 - val_loss: 0.4836 - val_accuracy: 0.9055 Epoch 56/199 128/6993 [..............................] - ETA: 0s - loss: 0.0484 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.0562 - accuracy: 0.9844 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0698 - accuracy: 0.9826 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0782 - accuracy: 0.9814 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0852 - accuracy: 0.9779 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0783 - accuracy: 0.9799 3328/6993 [=============>................] - ETA: 0s - loss: 0.0796 - accuracy: 0.9775 3968/6993 [================>.............] - ETA: 0s - loss: 0.0795 - accuracy: 0.9776 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0824 - accuracy: 0.9768 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0825 - accuracy: 0.9764 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0804 - accuracy: 0.9771 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0852 - accuracy: 0.9763 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0846 - accuracy: 0.9767 - val_loss: 0.5196 - val_accuracy: 0.9110 Epoch 57/199 128/6993 [..............................] - ETA: 0s - loss: 0.1468 - accuracy: 0.9531 768/6993 [==>...........................] - ETA: 0s - loss: 0.0749 - accuracy: 0.9792 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0829 - accuracy: 0.9766 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0720 - accuracy: 0.9785 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0654 - accuracy: 0.9798 3328/6993 [=============>................] - ETA: 0s - loss: 0.0742 - accuracy: 0.9769 4096/6993 [================>.............] - ETA: 0s - loss: 0.0735 - accuracy: 0.9780 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0762 - accuracy: 0.9782 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0806 - accuracy: 0.9769 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0805 - accuracy: 0.9770 6912/6993 [============================>.] - ETA: 0s - loss: 0.0825 - accuracy: 0.9764 6993/6993 [==============================] - 1s 102us/sample - loss: 0.0818 - accuracy: 0.9765 - val_loss: 0.4489 - val_accuracy: 0.9141 Epoch 58/199 128/6993 [..............................] - ETA: 0s - loss: 0.1109 - accuracy: 0.9531 640/6993 [=>............................] - ETA: 0s - loss: 0.1000 - accuracy: 0.9734 896/6993 [==>...........................] - ETA: 0s - loss: 0.0995 - accuracy: 0.9710 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0934 - accuracy: 0.9750 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0860 - accuracy: 0.9766 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0789 - accuracy: 0.9775 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0764 - accuracy: 0.9781 3200/6993 [============>.................] - ETA: 0s - loss: 0.0823 - accuracy: 0.9778 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0810 - accuracy: 0.9776 4352/6993 [=================>............] - ETA: 0s - loss: 0.0849 - accuracy: 0.9779 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0847 - accuracy: 0.9780 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0864 - accuracy: 0.9778 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0895 - accuracy: 0.9773 6993/6993 [==============================] - 1s 114us/sample - loss: 0.0938 - accuracy: 0.9777 - val_loss: 0.4217 - val_accuracy: 0.9181 Epoch 59/199 128/6993 [..............................] - ETA: 0s - loss: 0.1272 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.0769 - accuracy: 0.9721 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0754 - accuracy: 0.9794 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0637 - accuracy: 0.9820 3200/6993 [============>.................] - ETA: 0s - loss: 0.0714 - accuracy: 0.9828 3968/6993 [================>.............] - ETA: 0s - loss: 0.0706 - accuracy: 0.9836 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0664 - accuracy: 0.9842 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0705 - accuracy: 0.9833 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0790 - accuracy: 0.9818 6912/6993 [============================>.] - ETA: 0s - loss: 0.0787 - accuracy: 0.9813 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0800 - accuracy: 0.9811 - val_loss: 0.4807 - val_accuracy: 0.9039 Epoch 60/199 128/6993 [..............................] - ETA: 0s - loss: 0.0568 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.0625 - accuracy: 0.9859 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0655 - accuracy: 0.9822 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0657 - accuracy: 0.9829 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0753 - accuracy: 0.9807 3328/6993 [=============>................] - ETA: 0s - loss: 0.0813 - accuracy: 0.9799 4096/6993 [================>.............] - ETA: 0s - loss: 0.0901 - accuracy: 0.9768 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0956 - accuracy: 0.9761 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1019 - accuracy: 0.9760 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1022 - accuracy: 0.9758 6912/6993 [============================>.] - ETA: 0s - loss: 0.1035 - accuracy: 0.9758 6993/6993 [==============================] - 1s 91us/sample - loss: 0.1034 - accuracy: 0.9758 - val_loss: 0.4263 - val_accuracy: 0.9191 Epoch 61/199 128/6993 [..............................] - ETA: 0s - loss: 0.0314 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0590 - accuracy: 0.9866 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0685 - accuracy: 0.9880 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0820 - accuracy: 0.9844 3200/6993 [============>.................] - ETA: 0s - loss: 0.0805 - accuracy: 0.9837 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0816 - accuracy: 0.9827 4096/6993 [================>.............] - ETA: 0s - loss: 0.0768 - accuracy: 0.9824 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0728 - accuracy: 0.9833 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0740 - accuracy: 0.9822 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0749 - accuracy: 0.9816 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0747 - accuracy: 0.9811 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0734 - accuracy: 0.9810 6993/6993 [==============================] - 1s 114us/sample - loss: 0.0741 - accuracy: 0.9803 - val_loss: 0.4578 - val_accuracy: 0.9156 Epoch 62/199 128/6993 [..............................] - ETA: 0s - loss: 0.0254 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0701 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0645 - accuracy: 0.9851 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0559 - accuracy: 0.9866 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0598 - accuracy: 0.9839 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0671 - accuracy: 0.9822 3328/6993 [=============>................] - ETA: 0s - loss: 0.0679 - accuracy: 0.9820 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0700 - accuracy: 0.9818 4224/6993 [=================>............] - ETA: 0s - loss: 0.0800 - accuracy: 0.9804 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0774 - accuracy: 0.9809 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0788 - accuracy: 0.9807 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0834 - accuracy: 0.9793 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0833 - accuracy: 0.9787 6993/6993 [==============================] - 1s 116us/sample - loss: 0.0832 - accuracy: 0.9787 - val_loss: 0.5055 - val_accuracy: 0.9176 Epoch 63/199 128/6993 [..............................] - ETA: 0s - loss: 0.2025 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0943 - accuracy: 0.9753 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0725 - accuracy: 0.9818 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0863 - accuracy: 0.9798 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0976 - accuracy: 0.9783 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0928 - accuracy: 0.9782 4224/6993 [=================>............] - ETA: 0s - loss: 0.0909 - accuracy: 0.9789 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0880 - accuracy: 0.9785 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0914 - accuracy: 0.9781 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0841 - accuracy: 0.9793 6912/6993 [============================>.] - ETA: 0s - loss: 0.0788 - accuracy: 0.9800 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0783 - accuracy: 0.9800 - val_loss: 0.4549 - val_accuracy: 0.9176 Epoch 64/199 128/6993 [..............................] - ETA: 0s - loss: 0.0192 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0654 - accuracy: 0.9855 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0560 - accuracy: 0.9850 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0681 - accuracy: 0.9813 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0701 - accuracy: 0.9814 3200/6993 [============>.................] - ETA: 0s - loss: 0.0759 - accuracy: 0.9787 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0755 - accuracy: 0.9793 4096/6993 [================>.............] - ETA: 0s - loss: 0.0733 - accuracy: 0.9790 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0775 - accuracy: 0.9783 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0765 - accuracy: 0.9784 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0805 - accuracy: 0.9775 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0805 - accuracy: 0.9776 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0805 - accuracy: 0.9766 6912/6993 [============================>.] - ETA: 0s - loss: 0.0853 - accuracy: 0.9755 6993/6993 [==============================] - 1s 129us/sample - loss: 0.0851 - accuracy: 0.9754 - val_loss: 0.4615 - val_accuracy: 0.9191 Epoch 65/199 128/6993 [..............................] - ETA: 0s - loss: 0.1036 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.0884 - accuracy: 0.9750 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0844 - accuracy: 0.9781 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0789 - accuracy: 0.9775 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0890 - accuracy: 0.9754 3328/6993 [=============>................] - ETA: 0s - loss: 0.0761 - accuracy: 0.9796 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0783 - accuracy: 0.9792 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0815 - accuracy: 0.9792 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0798 - accuracy: 0.9792 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0815 - accuracy: 0.9787 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0867 - accuracy: 0.9773 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0908 - accuracy: 0.9767 - val_loss: 0.4405 - val_accuracy: 0.9166 Epoch 66/199 128/6993 [..............................] - ETA: 0s - loss: 0.1886 - accuracy: 0.9609 640/6993 [=>............................] - ETA: 0s - loss: 0.1124 - accuracy: 0.9688 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0844 - accuracy: 0.9781 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0804 - accuracy: 0.9782 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0781 - accuracy: 0.9799 3200/6993 [============>.................] - ETA: 0s - loss: 0.0841 - accuracy: 0.9797 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0809 - accuracy: 0.9805 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0728 - accuracy: 0.9820 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0736 - accuracy: 0.9809 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0765 - accuracy: 0.9810 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0740 - accuracy: 0.9814 6784/6993 [============================>.] - ETA: 0s - loss: 0.0780 - accuracy: 0.9808 6993/6993 [==============================] - 1s 108us/sample - loss: 0.0801 - accuracy: 0.9804 - val_loss: 0.5512 - val_accuracy: 0.9080 Epoch 67/199 128/6993 [..............................] - ETA: 0s - loss: 0.1601 - accuracy: 0.9531 512/6993 [=>............................] - ETA: 0s - loss: 0.0609 - accuracy: 0.9805 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0829 - accuracy: 0.9805 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0769 - accuracy: 0.9805 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0773 - accuracy: 0.9819 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0730 - accuracy: 0.9812 3072/6993 [============>.................] - ETA: 0s - loss: 0.0710 - accuracy: 0.9814 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0741 - accuracy: 0.9810 4224/6993 [=================>............] - ETA: 0s - loss: 0.0782 - accuracy: 0.9796 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0760 - accuracy: 0.9796 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0723 - accuracy: 0.9802 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0733 - accuracy: 0.9808 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0736 - accuracy: 0.9809 6993/6993 [==============================] - 1s 118us/sample - loss: 0.0797 - accuracy: 0.9803 - val_loss: 0.4349 - val_accuracy: 0.9247 Epoch 68/199 128/6993 [..............................] - ETA: 1s - loss: 0.0188 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0664 - accuracy: 0.9875 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0564 - accuracy: 0.9883 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0514 - accuracy: 0.9863 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0652 - accuracy: 0.9829 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0641 - accuracy: 0.9820 3072/6993 [============>.................] - ETA: 0s - loss: 0.0675 - accuracy: 0.9831 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0690 - accuracy: 0.9820 4352/6993 [=================>............] - ETA: 0s - loss: 0.0669 - accuracy: 0.9821 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0777 - accuracy: 0.9799 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0780 - accuracy: 0.9794 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0875 - accuracy: 0.9796 6912/6993 [============================>.] - ETA: 0s - loss: 0.0924 - accuracy: 0.9777 6993/6993 [==============================] - 1s 112us/sample - loss: 0.0923 - accuracy: 0.9778 - val_loss: 0.4855 - val_accuracy: 0.9201 Epoch 69/199 128/6993 [..............................] - ETA: 0s - loss: 0.0431 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0317 - accuracy: 0.9891 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0666 - accuracy: 0.9851 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0609 - accuracy: 0.9856 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0857 - accuracy: 0.9839 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0783 - accuracy: 0.9853 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0803 - accuracy: 0.9833 3072/6993 [============>.................] - ETA: 0s - loss: 0.0834 - accuracy: 0.9818 3456/6993 [=============>................] - ETA: 0s - loss: 0.0877 - accuracy: 0.9800 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0999 - accuracy: 0.9792 4352/6993 [=================>............] - ETA: 0s - loss: 0.1035 - accuracy: 0.9791 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0996 - accuracy: 0.9786 5504/6993 [======================>.......] - ETA: 0s - loss: 0.1023 - accuracy: 0.9771 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0991 - accuracy: 0.9775 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0960 - accuracy: 0.9778 6993/6993 [==============================] - 1s 140us/sample - loss: 0.0945 - accuracy: 0.9781 - val_loss: 0.4565 - val_accuracy: 0.9221 Epoch 70/199 128/6993 [..............................] - ETA: 1s - loss: 0.0718 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1310 - accuracy: 0.9818 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0931 - accuracy: 0.9867 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0848 - accuracy: 0.9860 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0748 - accuracy: 0.9857 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0828 - accuracy: 0.9830 3328/6993 [=============>................] - ETA: 0s - loss: 0.0820 - accuracy: 0.9829 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0798 - accuracy: 0.9826 4352/6993 [=================>............] - ETA: 0s - loss: 0.0811 - accuracy: 0.9821 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0821 - accuracy: 0.9815 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0855 - accuracy: 0.9801 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0818 - accuracy: 0.9804 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0809 - accuracy: 0.9800 6993/6993 [==============================] - 1s 110us/sample - loss: 0.0835 - accuracy: 0.9796 - val_loss: 0.4458 - val_accuracy: 0.9151 Epoch 71/199 128/6993 [..............................] - ETA: 0s - loss: 0.0743 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0761 - accuracy: 0.9779 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0625 - accuracy: 0.9830 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0599 - accuracy: 0.9829 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0639 - accuracy: 0.9821 3328/6993 [=============>................] - ETA: 0s - loss: 0.0628 - accuracy: 0.9832 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0625 - accuracy: 0.9846 4352/6993 [=================>............] - ETA: 0s - loss: 0.0599 - accuracy: 0.9853 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0602 - accuracy: 0.9846 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0609 - accuracy: 0.9842 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0631 - accuracy: 0.9833 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0643 - accuracy: 0.9836 - val_loss: 0.5027 - val_accuracy: 0.9237 Epoch 72/199 128/6993 [..............................] - ETA: 0s - loss: 0.0127 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.1001 - accuracy: 0.9740 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0894 - accuracy: 0.9759 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0878 - accuracy: 0.9746 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0761 - accuracy: 0.9788 3328/6993 [=============>................] - ETA: 0s - loss: 0.0784 - accuracy: 0.9799 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0781 - accuracy: 0.9810 4352/6993 [=================>............] - ETA: 0s - loss: 0.0736 - accuracy: 0.9814 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0706 - accuracy: 0.9818 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0723 - accuracy: 0.9819 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0720 - accuracy: 0.9816 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0719 - accuracy: 0.9814 - val_loss: 0.4879 - val_accuracy: 0.9181 Epoch 73/199 128/6993 [..............................] - ETA: 0s - loss: 0.0766 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0654 - accuracy: 0.9818 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0702 - accuracy: 0.9844 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0711 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0689 - accuracy: 0.9836 3200/6993 [============>.................] - ETA: 0s - loss: 0.0661 - accuracy: 0.9847 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0623 - accuracy: 0.9852 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0617 - accuracy: 0.9848 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0581 - accuracy: 0.9849 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0580 - accuracy: 0.9840 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0597 - accuracy: 0.9835 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0602 - accuracy: 0.9833 - val_loss: 0.5122 - val_accuracy: 0.9196 Epoch 74/199 128/6993 [..............................] - ETA: 0s - loss: 0.1574 - accuracy: 0.9531 640/6993 [=>............................] - ETA: 0s - loss: 0.0812 - accuracy: 0.9797 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1143 - accuracy: 0.9773 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1081 - accuracy: 0.9807 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0966 - accuracy: 0.9820 3200/6993 [============>.................] - ETA: 0s - loss: 0.0852 - accuracy: 0.9825 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0920 - accuracy: 0.9810 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0878 - accuracy: 0.9821 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0909 - accuracy: 0.9818 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0897 - accuracy: 0.9816 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0886 - accuracy: 0.9812 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0952 - accuracy: 0.9801 - val_loss: 0.5737 - val_accuracy: 0.9044 Epoch 75/199 128/6993 [..............................] - ETA: 0s - loss: 0.0360 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1010 - accuracy: 0.9805 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0735 - accuracy: 0.9837 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0700 - accuracy: 0.9824 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0677 - accuracy: 0.9840 3456/6993 [=============>................] - ETA: 0s - loss: 0.0644 - accuracy: 0.9838 4096/6993 [================>.............] - ETA: 0s - loss: 0.0622 - accuracy: 0.9839 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0658 - accuracy: 0.9825 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0675 - accuracy: 0.9825 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0710 - accuracy: 0.9820 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0752 - accuracy: 0.9811 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0754 - accuracy: 0.9808 - val_loss: 0.4709 - val_accuracy: 0.9166 Epoch 76/199 128/6993 [..............................] - ETA: 0s - loss: 0.0165 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0261 - accuracy: 0.9935 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0627 - accuracy: 0.9872 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0622 - accuracy: 0.9863 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1007 - accuracy: 0.9825 3328/6993 [=============>................] - ETA: 0s - loss: 0.0972 - accuracy: 0.9811 3968/6993 [================>.............] - ETA: 0s - loss: 0.0967 - accuracy: 0.9793 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0919 - accuracy: 0.9796 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0865 - accuracy: 0.9806 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0823 - accuracy: 0.9813 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0778 - accuracy: 0.9821 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0790 - accuracy: 0.9821 - val_loss: 0.5306 - val_accuracy: 0.9105 Epoch 77/199 128/6993 [..............................] - ETA: 1s - loss: 0.0669 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0501 - accuracy: 0.9844 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0763 - accuracy: 0.9812 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0706 - accuracy: 0.9827 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0641 - accuracy: 0.9835 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0818 - accuracy: 0.9797 3072/6993 [============>.................] - ETA: 0s - loss: 0.0767 - accuracy: 0.9808 3456/6993 [=============>................] - ETA: 0s - loss: 0.0789 - accuracy: 0.9800 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0775 - accuracy: 0.9806 3968/6993 [================>.............] - ETA: 0s - loss: 0.0771 - accuracy: 0.9798 4352/6993 [=================>............] - ETA: 0s - loss: 0.0819 - accuracy: 0.9795 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0814 - accuracy: 0.9792 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0783 - accuracy: 0.9797 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0826 - accuracy: 0.9800 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0827 - accuracy: 0.9795 6912/6993 [============================>.] - ETA: 0s - loss: 0.0833 - accuracy: 0.9786 6993/6993 [==============================] - 1s 136us/sample - loss: 0.0844 - accuracy: 0.9785 - val_loss: 0.4334 - val_accuracy: 0.9166 Epoch 78/199 128/6993 [..............................] - ETA: 0s - loss: 0.0245 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0912 - accuracy: 0.9766 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0743 - accuracy: 0.9787 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0706 - accuracy: 0.9814 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0667 - accuracy: 0.9840 3072/6993 [============>.................] - ETA: 0s - loss: 0.0693 - accuracy: 0.9837 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0736 - accuracy: 0.9814 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0745 - accuracy: 0.9822 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0737 - accuracy: 0.9819 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0721 - accuracy: 0.9827 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0804 - accuracy: 0.9812 6993/6993 [==============================] - 1s 99us/sample - loss: 0.0794 - accuracy: 0.9813 - val_loss: 0.4948 - val_accuracy: 0.9176 Epoch 79/199 128/6993 [..............................] - ETA: 0s - loss: 0.0953 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0612 - accuracy: 0.9870 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0597 - accuracy: 0.9837 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0629 - accuracy: 0.9844 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0577 - accuracy: 0.9852 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0667 - accuracy: 0.9840 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0627 - accuracy: 0.9849 4352/6993 [=================>............] - ETA: 0s - loss: 0.0684 - accuracy: 0.9839 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0685 - accuracy: 0.9850 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0729 - accuracy: 0.9838 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0749 - accuracy: 0.9831 6993/6993 [==============================] - 1s 103us/sample - loss: 0.0723 - accuracy: 0.9834 - val_loss: 0.4383 - val_accuracy: 0.9232 Epoch 80/199 128/6993 [..............................] - ETA: 0s - loss: 0.0958 - accuracy: 0.9609 768/6993 [==>...........................] - ETA: 0s - loss: 0.0403 - accuracy: 0.9805 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0360 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0456 - accuracy: 0.9854 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0495 - accuracy: 0.9857 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0491 - accuracy: 0.9862 3456/6993 [=============>................] - ETA: 0s - loss: 0.0574 - accuracy: 0.9855 4096/6993 [================>.............] - ETA: 0s - loss: 0.0637 - accuracy: 0.9844 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0636 - accuracy: 0.9835 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0635 - accuracy: 0.9838 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0641 - accuracy: 0.9835 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0613 - accuracy: 0.9839 6993/6993 [==============================] - 1s 102us/sample - loss: 0.0646 - accuracy: 0.9836 - val_loss: 0.5002 - val_accuracy: 0.9070 Epoch 81/199 128/6993 [..............................] - ETA: 0s - loss: 0.0481 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0626 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0591 - accuracy: 0.9822 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0614 - accuracy: 0.9824 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0582 - accuracy: 0.9829 3328/6993 [=============>................] - ETA: 0s - loss: 0.0595 - accuracy: 0.9832 3968/6993 [================>.............] - ETA: 0s - loss: 0.0679 - accuracy: 0.9831 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0668 - accuracy: 0.9829 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0654 - accuracy: 0.9830 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0642 - accuracy: 0.9839 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0751 - accuracy: 0.9824 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0753 - accuracy: 0.9818 - val_loss: 0.4863 - val_accuracy: 0.9181 Epoch 82/199 128/6993 [..............................] - ETA: 0s - loss: 0.0294 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0252 - accuracy: 0.9922 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0425 - accuracy: 0.9896 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0528 - accuracy: 0.9872 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0562 - accuracy: 0.9855 3200/6993 [============>.................] - ETA: 0s - loss: 0.0606 - accuracy: 0.9847 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0614 - accuracy: 0.9849 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0671 - accuracy: 0.9833 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0687 - accuracy: 0.9825 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0693 - accuracy: 0.9825 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0721 - accuracy: 0.9823 6784/6993 [============================>.] - ETA: 0s - loss: 0.0704 - accuracy: 0.9829 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0687 - accuracy: 0.9834 - val_loss: 0.5203 - val_accuracy: 0.9191 Epoch 83/199 128/6993 [..............................] - ETA: 0s - loss: 0.0777 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.0791 - accuracy: 0.9750 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0701 - accuracy: 0.9789 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0606 - accuracy: 0.9807 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0541 - accuracy: 0.9832 3200/6993 [============>.................] - ETA: 0s - loss: 0.0600 - accuracy: 0.9819 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0591 - accuracy: 0.9831 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0558 - accuracy: 0.9837 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0562 - accuracy: 0.9836 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0580 - accuracy: 0.9836 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0629 - accuracy: 0.9834 6784/6993 [============================>.] - ETA: 0s - loss: 0.0675 - accuracy: 0.9823 6993/6993 [==============================] - 1s 103us/sample - loss: 0.0670 - accuracy: 0.9827 - val_loss: 0.4853 - val_accuracy: 0.9135 Epoch 84/199 128/6993 [..............................] - ETA: 0s - loss: 0.0968 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0415 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0403 - accuracy: 0.9879 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0656 - accuracy: 0.9849 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0676 - accuracy: 0.9847 3328/6993 [=============>................] - ETA: 0s - loss: 0.0733 - accuracy: 0.9841 3968/6993 [================>.............] - ETA: 0s - loss: 0.0738 - accuracy: 0.9846 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0813 - accuracy: 0.9839 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0767 - accuracy: 0.9842 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0771 - accuracy: 0.9840 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0741 - accuracy: 0.9847 6993/6993 [==============================] - 1s 105us/sample - loss: 0.0758 - accuracy: 0.9846 - val_loss: 0.4692 - val_accuracy: 0.9237 Epoch 85/199 128/6993 [..............................] - ETA: 0s - loss: 0.0028 - accuracy: 1.0000 640/6993 [=>............................] - ETA: 0s - loss: 0.0358 - accuracy: 0.9937 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0329 - accuracy: 0.9931 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0281 - accuracy: 0.9941 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0318 - accuracy: 0.9927 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0409 - accuracy: 0.9910 3072/6993 [============>.................] - ETA: 0s - loss: 0.0488 - accuracy: 0.9899 3456/6993 [=============>................] - ETA: 0s - loss: 0.0515 - accuracy: 0.9896 3968/6993 [================>.............] - ETA: 0s - loss: 0.0570 - accuracy: 0.9869 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0572 - accuracy: 0.9866 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0581 - accuracy: 0.9863 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0557 - accuracy: 0.9868 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0539 - accuracy: 0.9877 6993/6993 [==============================] - 1s 120us/sample - loss: 0.0556 - accuracy: 0.9867 - val_loss: 0.5746 - val_accuracy: 0.9176 Epoch 86/199 128/6993 [..............................] - ETA: 0s - loss: 0.1005 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0723 - accuracy: 0.9859 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0879 - accuracy: 0.9797 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0767 - accuracy: 0.9818 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0676 - accuracy: 0.9840 3328/6993 [=============>................] - ETA: 0s - loss: 0.0740 - accuracy: 0.9826 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0721 - accuracy: 0.9830 4224/6993 [=================>............] - ETA: 0s - loss: 0.0727 - accuracy: 0.9825 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0709 - accuracy: 0.9829 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0739 - accuracy: 0.9833 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0750 - accuracy: 0.9834 6784/6993 [============================>.] - ETA: 0s - loss: 0.0735 - accuracy: 0.9833 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0749 - accuracy: 0.9833 - val_loss: 0.4491 - val_accuracy: 0.9252 Epoch 87/199 128/6993 [..............................] - ETA: 0s - loss: 0.0244 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0450 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0452 - accuracy: 0.9872 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0431 - accuracy: 0.9868 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0425 - accuracy: 0.9867 3200/6993 [============>.................] - ETA: 0s - loss: 0.0426 - accuracy: 0.9859 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0449 - accuracy: 0.9857 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0529 - accuracy: 0.9855 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0540 - accuracy: 0.9850 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0530 - accuracy: 0.9854 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0628 - accuracy: 0.9837 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0635 - accuracy: 0.9837 - val_loss: 0.4974 - val_accuracy: 0.9146 Epoch 88/199 128/6993 [..............................] - ETA: 0s - loss: 0.0648 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0569 - accuracy: 0.9818 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0698 - accuracy: 0.9837 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0599 - accuracy: 0.9868 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0642 - accuracy: 0.9833 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0649 - accuracy: 0.9830 4224/6993 [=================>............] - ETA: 0s - loss: 0.0694 - accuracy: 0.9825 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0741 - accuracy: 0.9830 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0757 - accuracy: 0.9824 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0697 - accuracy: 0.9839 6784/6993 [============================>.] - ETA: 0s - loss: 0.0710 - accuracy: 0.9842 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0725 - accuracy: 0.9841 - val_loss: 0.4889 - val_accuracy: 0.9312 Epoch 89/199 128/6993 [..............................] - ETA: 0s - loss: 0.0593 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0702 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0857 - accuracy: 0.9787 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0704 - accuracy: 0.9814 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0712 - accuracy: 0.9812 3200/6993 [============>.................] - ETA: 0s - loss: 0.0652 - accuracy: 0.9825 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0661 - accuracy: 0.9820 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0690 - accuracy: 0.9824 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0675 - accuracy: 0.9822 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0646 - accuracy: 0.9833 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0634 - accuracy: 0.9834 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0631 - accuracy: 0.9838 6993/6993 [==============================] - 1s 105us/sample - loss: 0.0639 - accuracy: 0.9838 - val_loss: 0.5256 - val_accuracy: 0.9237 Epoch 90/199 128/6993 [..............................] - ETA: 0s - loss: 0.0973 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0407 - accuracy: 0.9935 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0393 - accuracy: 0.9922 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0410 - accuracy: 0.9907 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0428 - accuracy: 0.9910 3200/6993 [============>.................] - ETA: 0s - loss: 0.0446 - accuracy: 0.9900 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0519 - accuracy: 0.9891 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0561 - accuracy: 0.9883 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0578 - accuracy: 0.9876 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0601 - accuracy: 0.9872 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0598 - accuracy: 0.9865 6993/6993 [==============================] - 1s 102us/sample - loss: 0.0609 - accuracy: 0.9864 - val_loss: 0.4433 - val_accuracy: 0.9302 Epoch 91/199 128/6993 [..............................] - ETA: 0s - loss: 0.0321 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0313 - accuracy: 0.9922 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0746 - accuracy: 0.9887 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0666 - accuracy: 0.9874 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0577 - accuracy: 0.9876 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0708 - accuracy: 0.9862 3328/6993 [=============>................] - ETA: 0s - loss: 0.0754 - accuracy: 0.9856 3968/6993 [================>.............] - ETA: 0s - loss: 0.0770 - accuracy: 0.9849 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0825 - accuracy: 0.9852 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0826 - accuracy: 0.9848 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0784 - accuracy: 0.9849 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0763 - accuracy: 0.9847 6993/6993 [==============================] - 1s 102us/sample - loss: 0.0748 - accuracy: 0.9848 - val_loss: 0.4999 - val_accuracy: 0.9237 Epoch 92/199 128/6993 [..............................] - ETA: 0s - loss: 0.0249 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1065 - accuracy: 0.9818 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1068 - accuracy: 0.9781 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1092 - accuracy: 0.9776 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0959 - accuracy: 0.9807 3456/6993 [=============>................] - ETA: 0s - loss: 0.0895 - accuracy: 0.9823 4096/6993 [================>.............] - ETA: 0s - loss: 0.0852 - accuracy: 0.9827 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0798 - accuracy: 0.9839 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0801 - accuracy: 0.9838 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0762 - accuracy: 0.9844 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0741 - accuracy: 0.9844 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0789 - accuracy: 0.9838 6993/6993 [==============================] - 1s 113us/sample - loss: 0.0792 - accuracy: 0.9840 - val_loss: 0.5121 - val_accuracy: 0.9242 Epoch 93/199 128/6993 [..............................] - ETA: 0s - loss: 0.0162 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9781 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0587 - accuracy: 0.9800 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0639 - accuracy: 0.9794 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0679 - accuracy: 0.9819 3072/6993 [============>.................] - ETA: 0s - loss: 0.0669 - accuracy: 0.9811 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0585 - accuracy: 0.9838 4352/6993 [=================>............] - ETA: 0s - loss: 0.0572 - accuracy: 0.9846 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0633 - accuracy: 0.9842 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0653 - accuracy: 0.9837 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0696 - accuracy: 0.9825 6912/6993 [============================>.] - ETA: 0s - loss: 0.0717 - accuracy: 0.9822 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0709 - accuracy: 0.9824 - val_loss: 0.4731 - val_accuracy: 0.9242 Epoch 94/199 128/6993 [..............................] - ETA: 0s - loss: 0.0057 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0434 - accuracy: 0.9866 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0466 - accuracy: 0.9863 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0574 - accuracy: 0.9825 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0627 - accuracy: 0.9834 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0631 - accuracy: 0.9830 4224/6993 [=================>............] - ETA: 0s - loss: 0.0636 - accuracy: 0.9839 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0634 - accuracy: 0.9831 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0712 - accuracy: 0.9824 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0759 - accuracy: 0.9821 6912/6993 [============================>.] - ETA: 0s - loss: 0.0742 - accuracy: 0.9826 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0736 - accuracy: 0.9827 - val_loss: 0.4823 - val_accuracy: 0.9201 Epoch 95/199 128/6993 [..............................] - ETA: 1s - loss: 0.0142 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0993 - accuracy: 0.9810 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0797 - accuracy: 0.9818 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0645 - accuracy: 0.9858 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0747 - accuracy: 0.9847 3456/6993 [=============>................] - ETA: 0s - loss: 0.0716 - accuracy: 0.9858 4096/6993 [================>.............] - ETA: 0s - loss: 0.0838 - accuracy: 0.9851 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0819 - accuracy: 0.9848 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0780 - accuracy: 0.9844 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0731 - accuracy: 0.9839 6912/6993 [============================>.] - ETA: 0s - loss: 0.0795 - accuracy: 0.9831 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0806 - accuracy: 0.9828 - val_loss: 0.5209 - val_accuracy: 0.9141 Epoch 96/199 128/6993 [..............................] - ETA: 0s - loss: 0.0502 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.0420 - accuracy: 0.9875 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0976 - accuracy: 0.9828 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0865 - accuracy: 0.9844 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0774 - accuracy: 0.9848 3200/6993 [============>.................] - ETA: 0s - loss: 0.0674 - accuracy: 0.9859 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0626 - accuracy: 0.9867 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0611 - accuracy: 0.9881 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0619 - accuracy: 0.9870 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0638 - accuracy: 0.9866 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0646 - accuracy: 0.9868 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0646 - accuracy: 0.9867 - val_loss: 0.4858 - val_accuracy: 0.9232 Epoch 97/199 128/6993 [..............................] - ETA: 0s - loss: 0.0340 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0279 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0353 - accuracy: 0.9901 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0433 - accuracy: 0.9893 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0387 - accuracy: 0.9896 3456/6993 [=============>................] - ETA: 0s - loss: 0.0544 - accuracy: 0.9855 4224/6993 [=================>............] - ETA: 0s - loss: 0.0523 - accuracy: 0.9870 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0588 - accuracy: 0.9864 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0557 - accuracy: 0.9867 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0595 - accuracy: 0.9860 6784/6993 [============================>.] - ETA: 0s - loss: 0.0570 - accuracy: 0.9863 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0567 - accuracy: 0.9863 - val_loss: 0.5233 - val_accuracy: 0.9201 Epoch 98/199 128/6993 [..............................] - ETA: 0s - loss: 0.2681 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0732 - accuracy: 0.9896 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0611 - accuracy: 0.9876 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0640 - accuracy: 0.9867 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0624 - accuracy: 0.9861 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0655 - accuracy: 0.9858 4224/6993 [=================>............] - ETA: 0s - loss: 0.0783 - accuracy: 0.9841 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0715 - accuracy: 0.9850 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0855 - accuracy: 0.9836 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0881 - accuracy: 0.9829 6784/6993 [============================>.] - ETA: 0s - loss: 0.0841 - accuracy: 0.9832 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0849 - accuracy: 0.9831 - val_loss: 0.5295 - val_accuracy: 0.9176 Epoch 99/199 128/6993 [..............................] - ETA: 0s - loss: 0.0228 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0602 - accuracy: 0.9855 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0483 - accuracy: 0.9874 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0527 - accuracy: 0.9874 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0524 - accuracy: 0.9878 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0500 - accuracy: 0.9880 4224/6993 [=================>............] - ETA: 0s - loss: 0.0516 - accuracy: 0.9875 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0523 - accuracy: 0.9870 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0521 - accuracy: 0.9866 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0524 - accuracy: 0.9866 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0532 - accuracy: 0.9862 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0523 - accuracy: 0.9863 - val_loss: 0.6005 - val_accuracy: 0.9191 Epoch 100/199 128/6993 [..............................] - ETA: 1s - loss: 0.2247 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0699 - accuracy: 0.9870 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0734 - accuracy: 0.9858 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0664 - accuracy: 0.9873 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0815 - accuracy: 0.9847 3328/6993 [=============>................] - ETA: 0s - loss: 0.0787 - accuracy: 0.9847 3968/6993 [================>.............] - ETA: 0s - loss: 0.0763 - accuracy: 0.9851 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0759 - accuracy: 0.9844 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0841 - accuracy: 0.9848 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0815 - accuracy: 0.9852 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0806 - accuracy: 0.9852 6912/6993 [============================>.] - ETA: 0s - loss: 0.0781 - accuracy: 0.9857 6993/6993 [==============================] - 1s 106us/sample - loss: 0.0848 - accuracy: 0.9856 - val_loss: 0.5614 - val_accuracy: 0.9196 Epoch 101/199 128/6993 [..............................] - ETA: 0s - loss: 0.0300 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0471 - accuracy: 0.9922 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0440 - accuracy: 0.9887 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0487 - accuracy: 0.9880 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0446 - accuracy: 0.9890 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0522 - accuracy: 0.9877 3200/6993 [============>.................] - ETA: 0s - loss: 0.0515 - accuracy: 0.9878 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0551 - accuracy: 0.9867 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0511 - accuracy: 0.9870 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0493 - accuracy: 0.9870 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0499 - accuracy: 0.9862 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0539 - accuracy: 0.9868 6993/6993 [==============================] - 1s 107us/sample - loss: 0.0550 - accuracy: 0.9867 - val_loss: 0.5540 - val_accuracy: 0.9257 Epoch 102/199 128/6993 [..............................] - ETA: 0s - loss: 0.0288 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0429 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0533 - accuracy: 0.9879 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0460 - accuracy: 0.9902 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0528 - accuracy: 0.9886 3456/6993 [=============>................] - ETA: 0s - loss: 0.0647 - accuracy: 0.9864 4096/6993 [================>.............] - ETA: 0s - loss: 0.0624 - accuracy: 0.9861 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0750 - accuracy: 0.9854 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0787 - accuracy: 0.9844 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0746 - accuracy: 0.9847 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0721 - accuracy: 0.9851 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0723 - accuracy: 0.9850 - val_loss: 0.5333 - val_accuracy: 0.9232 Epoch 103/199 128/6993 [..............................] - ETA: 0s - loss: 0.1134 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0548 - accuracy: 0.9833 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0475 - accuracy: 0.9850 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0620 - accuracy: 0.9835 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0641 - accuracy: 0.9837 3456/6993 [=============>................] - ETA: 0s - loss: 0.0541 - accuracy: 0.9861 4096/6993 [================>.............] - ETA: 0s - loss: 0.0580 - accuracy: 0.9861 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0570 - accuracy: 0.9854 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0646 - accuracy: 0.9842 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0684 - accuracy: 0.9842 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0718 - accuracy: 0.9838 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0719 - accuracy: 0.9837 - val_loss: 0.5357 - val_accuracy: 0.9247 Epoch 104/199 128/6993 [..............................] - ETA: 0s - loss: 0.0527 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1287 - accuracy: 0.9818 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1133 - accuracy: 0.9811 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0920 - accuracy: 0.9825 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0785 - accuracy: 0.9844 3456/6993 [=============>................] - ETA: 0s - loss: 0.0710 - accuracy: 0.9847 4096/6993 [================>.............] - ETA: 0s - loss: 0.0704 - accuracy: 0.9849 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0676 - accuracy: 0.9846 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0711 - accuracy: 0.9844 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0697 - accuracy: 0.9849 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0698 - accuracy: 0.9851 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0686 - accuracy: 0.9851 - val_loss: 0.5510 - val_accuracy: 0.9252 Epoch 105/199 128/6993 [..............................] - ETA: 1s - loss: 0.0666 - accuracy: 0.9531 768/6993 [==>...........................] - ETA: 0s - loss: 0.1065 - accuracy: 0.9688 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0868 - accuracy: 0.9760 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0779 - accuracy: 0.9787 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0764 - accuracy: 0.9800 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0699 - accuracy: 0.9810 4224/6993 [=================>............] - ETA: 0s - loss: 0.0674 - accuracy: 0.9813 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0665 - accuracy: 0.9825 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0722 - accuracy: 0.9818 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0724 - accuracy: 0.9823 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0699 - accuracy: 0.9833 - val_loss: 0.5497 - val_accuracy: 0.9166 Epoch 106/199 128/6993 [..............................] - ETA: 1s - loss: 0.0726 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.0698 - accuracy: 0.9818 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0794 - accuracy: 0.9830 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0800 - accuracy: 0.9858 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0931 - accuracy: 0.9840 3456/6993 [=============>................] - ETA: 0s - loss: 0.0882 - accuracy: 0.9847 4096/6993 [================>.............] - ETA: 0s - loss: 0.0886 - accuracy: 0.9849 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0843 - accuracy: 0.9850 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0855 - accuracy: 0.9849 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0818 - accuracy: 0.9847 6784/6993 [============================>.] - ETA: 0s - loss: 0.0799 - accuracy: 0.9848 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0808 - accuracy: 0.9847 - val_loss: 0.4682 - val_accuracy: 0.9226 Epoch 107/199 128/6993 [..............................] - ETA: 0s - loss: 0.0156 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0541 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0462 - accuracy: 0.9879 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0532 - accuracy: 0.9863 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0533 - accuracy: 0.9855 3456/6993 [=============>................] - ETA: 0s - loss: 0.0480 - accuracy: 0.9870 4224/6993 [=================>............] - ETA: 0s - loss: 0.0495 - accuracy: 0.9870 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0507 - accuracy: 0.9875 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0543 - accuracy: 0.9865 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0515 - accuracy: 0.9870 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0510 - accuracy: 0.9871 - val_loss: 0.5343 - val_accuracy: 0.9201 Epoch 108/199 128/6993 [..............................] - ETA: 0s - loss: 0.0088 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0569 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0591 - accuracy: 0.9851 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0564 - accuracy: 0.9862 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0588 - accuracy: 0.9865 3456/6993 [=============>................] - ETA: 0s - loss: 0.0562 - accuracy: 0.9873 4096/6993 [================>.............] - ETA: 0s - loss: 0.0547 - accuracy: 0.9883 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0507 - accuracy: 0.9889 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0500 - accuracy: 0.9893 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0495 - accuracy: 0.9890 6912/6993 [============================>.] - ETA: 0s - loss: 0.0551 - accuracy: 0.9873 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0552 - accuracy: 0.9873 - val_loss: 0.6763 - val_accuracy: 0.9161 Epoch 109/199 128/6993 [..............................] - ETA: 0s - loss: 0.0747 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.0800 - accuracy: 0.9750 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0699 - accuracy: 0.9789 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0669 - accuracy: 0.9812 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0694 - accuracy: 0.9823 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0721 - accuracy: 0.9820 3456/6993 [=============>................] - ETA: 0s - loss: 0.0833 - accuracy: 0.9815 3968/6993 [================>.............] - ETA: 0s - loss: 0.0988 - accuracy: 0.9806 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0976 - accuracy: 0.9816 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0990 - accuracy: 0.9822 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0971 - accuracy: 0.9812 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0947 - accuracy: 0.9818 6784/6993 [============================>.] - ETA: 0s - loss: 0.0893 - accuracy: 0.9825 6993/6993 [==============================] - 1s 110us/sample - loss: 0.0868 - accuracy: 0.9830 - val_loss: 0.4879 - val_accuracy: 0.9247 Epoch 110/199 128/6993 [..............................] - ETA: 0s - loss: 0.0242 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0149 - accuracy: 0.9961 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0336 - accuracy: 0.9929 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0440 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0540 - accuracy: 0.9855 3456/6993 [=============>................] - ETA: 0s - loss: 0.0533 - accuracy: 0.9867 4096/6993 [================>.............] - ETA: 0s - loss: 0.0493 - accuracy: 0.9873 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0499 - accuracy: 0.9873 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0473 - accuracy: 0.9881 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0534 - accuracy: 0.9874 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0560 - accuracy: 0.9868 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0569 - accuracy: 0.9870 - val_loss: 0.5488 - val_accuracy: 0.9221 Epoch 111/199 128/6993 [..............................] - ETA: 0s - loss: 0.0670 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0832 - accuracy: 0.9833 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0793 - accuracy: 0.9863 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0827 - accuracy: 0.9853 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0777 - accuracy: 0.9851 3456/6993 [=============>................] - ETA: 0s - loss: 0.0693 - accuracy: 0.9864 4096/6993 [================>.............] - ETA: 0s - loss: 0.0808 - accuracy: 0.9868 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0840 - accuracy: 0.9850 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0856 - accuracy: 0.9849 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0818 - accuracy: 0.9852 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0789 - accuracy: 0.9854 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0805 - accuracy: 0.9858 - val_loss: 0.5402 - val_accuracy: 0.9232 Epoch 112/199 128/6993 [..............................] - ETA: 1s - loss: 0.0051 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0608 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1039 - accuracy: 0.9837 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0904 - accuracy: 0.9862 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0859 - accuracy: 0.9858 3456/6993 [=============>................] - ETA: 0s - loss: 0.0811 - accuracy: 0.9858 4224/6993 [=================>............] - ETA: 0s - loss: 0.0838 - accuracy: 0.9844 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0877 - accuracy: 0.9838 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0807 - accuracy: 0.9851 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0801 - accuracy: 0.9840 6784/6993 [============================>.] - ETA: 0s - loss: 0.0790 - accuracy: 0.9833 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0789 - accuracy: 0.9833 - val_loss: 0.5574 - val_accuracy: 0.9211 Epoch 113/199 128/6993 [..............................] - ETA: 0s - loss: 0.2134 - accuracy: 0.9531 768/6993 [==>...........................] - ETA: 0s - loss: 0.0637 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0498 - accuracy: 0.9872 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0412 - accuracy: 0.9893 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0410 - accuracy: 0.9892 3456/6993 [=============>................] - ETA: 0s - loss: 0.0431 - accuracy: 0.9890 4096/6993 [================>.............] - ETA: 0s - loss: 0.0418 - accuracy: 0.9883 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0464 - accuracy: 0.9876 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0541 - accuracy: 0.9872 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0508 - accuracy: 0.9880 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0509 - accuracy: 0.9882 6784/6993 [============================>.] - ETA: 0s - loss: 0.0538 - accuracy: 0.9879 6993/6993 [==============================] - 1s 99us/sample - loss: 0.0540 - accuracy: 0.9878 - val_loss: 0.5723 - val_accuracy: 0.9232 Epoch 114/199 128/6993 [..............................] - ETA: 0s - loss: 0.1259 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0558 - accuracy: 0.9844 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0593 - accuracy: 0.9850 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0541 - accuracy: 0.9862 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0638 - accuracy: 0.9840 3456/6993 [=============>................] - ETA: 0s - loss: 0.0597 - accuracy: 0.9844 4096/6993 [================>.............] - ETA: 0s - loss: 0.0559 - accuracy: 0.9854 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0539 - accuracy: 0.9858 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0541 - accuracy: 0.9856 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0605 - accuracy: 0.9844 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0637 - accuracy: 0.9848 - val_loss: 0.5121 - val_accuracy: 0.9232 Epoch 115/199 128/6993 [..............................] - ETA: 0s - loss: 0.0184 - accuracy: 0.9922 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0914 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0638 - accuracy: 0.9883 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0557 - accuracy: 0.9889 3072/6993 [============>.................] - ETA: 0s - loss: 0.0515 - accuracy: 0.9886 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0521 - accuracy: 0.9878 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0602 - accuracy: 0.9875 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0594 - accuracy: 0.9875 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0578 - accuracy: 0.9875 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0577 - accuracy: 0.9861 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0607 - accuracy: 0.9860 - val_loss: 0.6895 - val_accuracy: 0.9146 Epoch 116/199 128/6993 [..............................] - ETA: 0s - loss: 0.1342 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0785 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9872 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1059 - accuracy: 0.9849 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0940 - accuracy: 0.9859 3328/6993 [=============>................] - ETA: 0s - loss: 0.0855 - accuracy: 0.9856 3968/6993 [================>.............] - ETA: 0s - loss: 0.0835 - accuracy: 0.9859 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0750 - accuracy: 0.9872 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0709 - accuracy: 0.9875 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0691 - accuracy: 0.9875 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0663 - accuracy: 0.9878 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0624 - accuracy: 0.9883 - val_loss: 0.5951 - val_accuracy: 0.9191 Epoch 117/199 128/6993 [..............................] - ETA: 1s - loss: 0.1442 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0499 - accuracy: 0.9870 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0457 - accuracy: 0.9886 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0648 - accuracy: 0.9876 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0675 - accuracy: 0.9872 3456/6993 [=============>................] - ETA: 0s - loss: 0.0642 - accuracy: 0.9864 4224/6993 [=================>............] - ETA: 0s - loss: 0.0586 - accuracy: 0.9872 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0593 - accuracy: 0.9868 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0582 - accuracy: 0.9868 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0588 - accuracy: 0.9873 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0563 - accuracy: 0.9872 6912/6993 [============================>.] - ETA: 0s - loss: 0.0558 - accuracy: 0.9871 6993/6993 [==============================] - 1s 106us/sample - loss: 0.0559 - accuracy: 0.9868 - val_loss: 0.6277 - val_accuracy: 0.9232 Epoch 118/199 128/6993 [..............................] - ETA: 0s - loss: 0.0828 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.0646 - accuracy: 0.9891 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0648 - accuracy: 0.9870 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0819 - accuracy: 0.9832 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0663 - accuracy: 0.9852 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0805 - accuracy: 0.9823 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0768 - accuracy: 0.9830 4096/6993 [================>.............] - ETA: 0s - loss: 0.0732 - accuracy: 0.9836 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0794 - accuracy: 0.9832 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0797 - accuracy: 0.9833 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0738 - accuracy: 0.9842 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0710 - accuracy: 0.9848 - val_loss: 0.6567 - val_accuracy: 0.9257 Epoch 119/199 128/6993 [..............................] - ETA: 0s - loss: 0.0724 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0261 - accuracy: 0.9933 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0418 - accuracy: 0.9915 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0588 - accuracy: 0.9881 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9864 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0761 - accuracy: 0.9872 4224/6993 [=================>............] - ETA: 0s - loss: 0.0710 - accuracy: 0.9877 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0688 - accuracy: 0.9881 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0731 - accuracy: 0.9869 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0710 - accuracy: 0.9873 6784/6993 [============================>.] - ETA: 0s - loss: 0.0695 - accuracy: 0.9872 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0720 - accuracy: 0.9870 - val_loss: 0.5938 - val_accuracy: 0.9277 Epoch 120/199 128/6993 [..............................] - ETA: 0s - loss: 0.0096 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0419 - accuracy: 0.9900 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0394 - accuracy: 0.9883 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0630 - accuracy: 0.9881 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0753 - accuracy: 0.9879 3456/6993 [=============>................] - ETA: 0s - loss: 0.0730 - accuracy: 0.9858 4096/6993 [================>.............] - ETA: 0s - loss: 0.0659 - accuracy: 0.9871 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0668 - accuracy: 0.9869 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0654 - accuracy: 0.9866 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0649 - accuracy: 0.9859 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0635 - accuracy: 0.9862 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0633 - accuracy: 0.9863 - val_loss: 0.6023 - val_accuracy: 0.9206 Epoch 121/199 128/6993 [..............................] - ETA: 1s - loss: 0.1125 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0581 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0518 - accuracy: 0.9865 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0569 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0594 - accuracy: 0.9885 3200/6993 [============>.................] - ETA: 0s - loss: 0.0613 - accuracy: 0.9875 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0736 - accuracy: 0.9859 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0675 - accuracy: 0.9871 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0678 - accuracy: 0.9865 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0683 - accuracy: 0.9862 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0679 - accuracy: 0.9861 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0666 - accuracy: 0.9863 - val_loss: 0.5974 - val_accuracy: 0.9262 Epoch 122/199 128/6993 [..............................] - ETA: 0s - loss: 0.0732 - accuracy: 0.9688 896/6993 [==>...........................] - ETA: 0s - loss: 0.0836 - accuracy: 0.9821 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0952 - accuracy: 0.9850 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0883 - accuracy: 0.9862 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0815 - accuracy: 0.9851 3456/6993 [=============>................] - ETA: 0s - loss: 0.0747 - accuracy: 0.9850 4096/6993 [================>.............] - ETA: 0s - loss: 0.0690 - accuracy: 0.9856 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0852 - accuracy: 0.9867 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0798 - accuracy: 0.9868 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0770 - accuracy: 0.9867 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0754 - accuracy: 0.9868 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0805 - accuracy: 0.9868 - val_loss: 0.5485 - val_accuracy: 0.9176 Epoch 123/199 128/6993 [..............................] - ETA: 0s - loss: 0.1263 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0815 - accuracy: 0.9792 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0923 - accuracy: 0.9797 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0815 - accuracy: 0.9816 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0773 - accuracy: 0.9844 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0789 - accuracy: 0.9858 3456/6993 [=============>................] - ETA: 0s - loss: 0.0798 - accuracy: 0.9861 4096/6993 [================>.............] - ETA: 0s - loss: 0.0789 - accuracy: 0.9851 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0791 - accuracy: 0.9859 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0787 - accuracy: 0.9856 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0767 - accuracy: 0.9859 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0800 - accuracy: 0.9856 - val_loss: 0.6508 - val_accuracy: 0.9226 Epoch 124/199 128/6993 [..............................] - ETA: 1s - loss: 0.0901 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0711 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0893 - accuracy: 0.9844 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0739 - accuracy: 0.9854 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0740 - accuracy: 0.9844 3072/6993 [============>.................] - ETA: 0s - loss: 0.0711 - accuracy: 0.9854 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0667 - accuracy: 0.9860 4224/6993 [=================>............] - ETA: 0s - loss: 0.0702 - accuracy: 0.9853 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0829 - accuracy: 0.9844 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0904 - accuracy: 0.9833 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0851 - accuracy: 0.9839 6912/6993 [============================>.] - ETA: 0s - loss: 0.0855 - accuracy: 0.9839 6993/6993 [==============================] - 1s 103us/sample - loss: 0.0854 - accuracy: 0.9840 - val_loss: 0.5360 - val_accuracy: 0.9191 Epoch 125/199 128/6993 [..............................] - ETA: 0s - loss: 0.0372 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0819 - accuracy: 0.9922 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0679 - accuracy: 0.9905 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0625 - accuracy: 0.9888 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0647 - accuracy: 0.9848 3072/6993 [============>.................] - ETA: 0s - loss: 0.0584 - accuracy: 0.9857 3968/6993 [================>.............] - ETA: 0s - loss: 0.0511 - accuracy: 0.9877 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0716 - accuracy: 0.9861 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0695 - accuracy: 0.9865 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0685 - accuracy: 0.9857 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0666 - accuracy: 0.9861 6912/6993 [============================>.] - ETA: 0s - loss: 0.0656 - accuracy: 0.9861 6993/6993 [==============================] - 1s 102us/sample - loss: 0.0650 - accuracy: 0.9863 - val_loss: 0.5426 - val_accuracy: 0.9257 Epoch 126/199 128/6993 [..............................] - ETA: 0s - loss: 0.1681 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.1217 - accuracy: 0.9797 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0878 - accuracy: 0.9800 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0929 - accuracy: 0.9808 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0755 - accuracy: 0.9830 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0798 - accuracy: 0.9844 3328/6993 [=============>................] - ETA: 0s - loss: 0.0738 - accuracy: 0.9862 4096/6993 [================>.............] - ETA: 0s - loss: 0.0814 - accuracy: 0.9854 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0793 - accuracy: 0.9844 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0759 - accuracy: 0.9847 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0700 - accuracy: 0.9857 6912/6993 [============================>.] - ETA: 0s - loss: 0.0715 - accuracy: 0.9851 6993/6993 [==============================] - 1s 103us/sample - loss: 0.0721 - accuracy: 0.9850 - val_loss: 0.5660 - val_accuracy: 0.9211 Epoch 127/199 128/6993 [..............................] - ETA: 0s - loss: 0.0171 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0725 - accuracy: 0.9857 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0578 - accuracy: 0.9870 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0650 - accuracy: 0.9873 3200/6993 [============>.................] - ETA: 0s - loss: 0.0641 - accuracy: 0.9872 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0765 - accuracy: 0.9865 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0732 - accuracy: 0.9866 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0701 - accuracy: 0.9867 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0696 - accuracy: 0.9872 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0734 - accuracy: 0.9867 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0715 - accuracy: 0.9864 - val_loss: 0.5767 - val_accuracy: 0.9226 Epoch 128/199 128/6993 [..............................] - ETA: 0s - loss: 0.0174 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0827 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0573 - accuracy: 0.9893 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0605 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0612 - accuracy: 0.9881 3328/6993 [=============>................] - ETA: 0s - loss: 0.0739 - accuracy: 0.9877 3968/6993 [================>.............] - ETA: 0s - loss: 0.0751 - accuracy: 0.9869 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0822 - accuracy: 0.9867 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0791 - accuracy: 0.9866 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0744 - accuracy: 0.9875 6784/6993 [============================>.] - ETA: 0s - loss: 0.0726 - accuracy: 0.9873 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0718 - accuracy: 0.9874 - val_loss: 0.5997 - val_accuracy: 0.9287 Epoch 129/199 128/6993 [..............................] - ETA: 0s - loss: 0.1903 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1068 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0768 - accuracy: 0.9844 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0763 - accuracy: 0.9829 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0757 - accuracy: 0.9847 3456/6993 [=============>................] - ETA: 0s - loss: 0.0714 - accuracy: 0.9852 4096/6993 [================>.............] - ETA: 0s - loss: 0.0690 - accuracy: 0.9854 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0717 - accuracy: 0.9848 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0739 - accuracy: 0.9840 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0695 - accuracy: 0.9850 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0703 - accuracy: 0.9848 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0696 - accuracy: 0.9851 - val_loss: 0.6097 - val_accuracy: 0.9242 Epoch 130/199 128/6993 [..............................] - ETA: 0s - loss: 0.0208 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1083 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9879 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0587 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0605 - accuracy: 0.9859 3456/6993 [=============>................] - ETA: 0s - loss: 0.0588 - accuracy: 0.9867 4096/6993 [================>.............] - ETA: 0s - loss: 0.0692 - accuracy: 0.9854 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0657 - accuracy: 0.9861 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0709 - accuracy: 0.9860 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0732 - accuracy: 0.9852 6784/6993 [============================>.] - ETA: 0s - loss: 0.0727 - accuracy: 0.9850 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0714 - accuracy: 0.9853 - val_loss: 0.5903 - val_accuracy: 0.9267 Epoch 131/199 128/6993 [..............................] - ETA: 1s - loss: 0.0412 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0642 - accuracy: 0.9844 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0523 - accuracy: 0.9857 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0561 - accuracy: 0.9874 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0563 - accuracy: 0.9878 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0521 - accuracy: 0.9880 4224/6993 [=================>............] - ETA: 0s - loss: 0.0509 - accuracy: 0.9879 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0546 - accuracy: 0.9877 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0600 - accuracy: 0.9869 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0655 - accuracy: 0.9863 6784/6993 [============================>.] - ETA: 0s - loss: 0.0737 - accuracy: 0.9863 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0755 - accuracy: 0.9860 - val_loss: 0.5276 - val_accuracy: 0.9242 Epoch 132/199 128/6993 [..............................] - ETA: 1s - loss: 0.0101 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0314 - accuracy: 0.9935 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0222 - accuracy: 0.9950 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0307 - accuracy: 0.9945 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0365 - accuracy: 0.9922 3456/6993 [=============>................] - ETA: 0s - loss: 0.0390 - accuracy: 0.9905 4096/6993 [================>.............] - ETA: 0s - loss: 0.0404 - accuracy: 0.9907 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0482 - accuracy: 0.9884 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0482 - accuracy: 0.9879 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0469 - accuracy: 0.9880 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0524 - accuracy: 0.9869 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0552 - accuracy: 0.9871 - val_loss: 0.6207 - val_accuracy: 0.9252 Epoch 133/199 128/6993 [..............................] - ETA: 0s - loss: 0.1270 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.0802 - accuracy: 0.9788 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0579 - accuracy: 0.9837 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0441 - accuracy: 0.9876 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0566 - accuracy: 0.9865 3456/6993 [=============>................] - ETA: 0s - loss: 0.0633 - accuracy: 0.9855 4096/6993 [================>.............] - ETA: 0s - loss: 0.0632 - accuracy: 0.9861 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0721 - accuracy: 0.9865 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0747 - accuracy: 0.9859 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0716 - accuracy: 0.9862 6784/6993 [============================>.] - ETA: 0s - loss: 0.0667 - accuracy: 0.9863 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0665 - accuracy: 0.9864 - val_loss: 0.5717 - val_accuracy: 0.9277 Epoch 134/199 128/6993 [..............................] - ETA: 0s - loss: 0.0969 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0270 - accuracy: 0.9948 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0561 - accuracy: 0.9914 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0506 - accuracy: 0.9922 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0467 - accuracy: 0.9922 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0513 - accuracy: 0.9904 3328/6993 [=============>................] - ETA: 0s - loss: 0.0719 - accuracy: 0.9883 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0703 - accuracy: 0.9875 4352/6993 [=================>............] - ETA: 0s - loss: 0.0665 - accuracy: 0.9878 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0647 - accuracy: 0.9875 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0594 - accuracy: 0.9884 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0629 - accuracy: 0.9880 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0660 - accuracy: 0.9872 6993/6993 [==============================] - 1s 114us/sample - loss: 0.0645 - accuracy: 0.9874 - val_loss: 0.4676 - val_accuracy: 0.9302 Epoch 135/199 128/6993 [..............................] - ETA: 0s - loss: 0.0054 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0394 - accuracy: 0.9922 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0279 - accuracy: 0.9928 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0374 - accuracy: 0.9926 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0604 - accuracy: 0.9911 3456/6993 [=============>................] - ETA: 0s - loss: 0.0607 - accuracy: 0.9910 4224/6993 [=================>............] - ETA: 0s - loss: 0.0696 - accuracy: 0.9889 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0619 - accuracy: 0.9895 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0624 - accuracy: 0.9889 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0587 - accuracy: 0.9892 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0565 - accuracy: 0.9893 - val_loss: 0.5378 - val_accuracy: 0.9297 Epoch 136/199 128/6993 [..............................] - ETA: 1s - loss: 0.0076 - accuracy: 1.0000 512/6993 [=>............................] - ETA: 1s - loss: 0.0847 - accuracy: 0.9863 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0507 - accuracy: 0.9893 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0469 - accuracy: 0.9886 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0677 - accuracy: 0.9860 3328/6993 [=============>................] - ETA: 0s - loss: 0.0561 - accuracy: 0.9883 3968/6993 [================>.............] - ETA: 0s - loss: 0.0530 - accuracy: 0.9889 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0582 - accuracy: 0.9887 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0631 - accuracy: 0.9880 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0729 - accuracy: 0.9875 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0722 - accuracy: 0.9875 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0698 - accuracy: 0.9877 - val_loss: 0.5861 - val_accuracy: 0.9317 Epoch 137/199 128/6993 [..............................] - ETA: 1s - loss: 0.0021 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0673 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0633 - accuracy: 0.9844 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0546 - accuracy: 0.9853 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0703 - accuracy: 0.9840 3456/6993 [=============>................] - ETA: 0s - loss: 0.0741 - accuracy: 0.9850 4096/6993 [================>.............] - ETA: 0s - loss: 0.0686 - accuracy: 0.9861 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0654 - accuracy: 0.9854 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0645 - accuracy: 0.9855 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0662 - accuracy: 0.9854 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0663 - accuracy: 0.9861 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0638 - accuracy: 0.9864 - val_loss: 0.5281 - val_accuracy: 0.9297 Epoch 138/199 128/6993 [..............................] - ETA: 0s - loss: 0.0801 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0614 - accuracy: 0.9911 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0606 - accuracy: 0.9902 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0546 - accuracy: 0.9913 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0554 - accuracy: 0.9915 3456/6993 [=============>................] - ETA: 0s - loss: 0.0628 - accuracy: 0.9913 4224/6993 [=================>............] - ETA: 0s - loss: 0.0588 - accuracy: 0.9915 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0584 - accuracy: 0.9910 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0542 - accuracy: 0.9909 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0569 - accuracy: 0.9896 6912/6993 [============================>.] - ETA: 0s - loss: 0.0599 - accuracy: 0.9893 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0599 - accuracy: 0.9893 - val_loss: 0.6692 - val_accuracy: 0.9242 Epoch 139/199 128/6993 [..............................] - ETA: 0s - loss: 0.1379 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1308 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0999 - accuracy: 0.9844 2048/6993 [=======>......................] - ETA: 0s - loss: 0.1091 - accuracy: 0.9844 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0947 - accuracy: 0.9851 3456/6993 [=============>................] - ETA: 0s - loss: 0.0843 - accuracy: 0.9864 4096/6993 [================>.............] - ETA: 0s - loss: 0.0772 - accuracy: 0.9863 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0743 - accuracy: 0.9861 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0751 - accuracy: 0.9853 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0694 - accuracy: 0.9860 6784/6993 [============================>.] - ETA: 0s - loss: 0.0694 - accuracy: 0.9866 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0698 - accuracy: 0.9864 - val_loss: 0.6079 - val_accuracy: 0.9262 Epoch 140/199 128/6993 [..............................] - ETA: 0s - loss: 0.0083 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0277 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0334 - accuracy: 0.9893 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0390 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0435 - accuracy: 0.9888 3328/6993 [=============>................] - ETA: 0s - loss: 0.0533 - accuracy: 0.9886 3968/6993 [================>.............] - ETA: 0s - loss: 0.0646 - accuracy: 0.9871 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0684 - accuracy: 0.9874 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0683 - accuracy: 0.9875 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0659 - accuracy: 0.9882 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0629 - accuracy: 0.9884 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0634 - accuracy: 0.9884 - val_loss: 0.6272 - val_accuracy: 0.9221 Epoch 141/199 128/6993 [..............................] - ETA: 0s - loss: 0.0261 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0363 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0807 - accuracy: 0.9872 2304/6993 [========>.....................] - ETA: 0s - loss: 0.1058 - accuracy: 0.9852 2944/6993 [===========>..................] - ETA: 0s - loss: 0.1149 - accuracy: 0.9844 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1101 - accuracy: 0.9847 4352/6993 [=================>............] - ETA: 0s - loss: 0.1119 - accuracy: 0.9846 4992/6993 [====================>.........] - ETA: 0s - loss: 0.1030 - accuracy: 0.9850 5632/6993 [=======================>......] - ETA: 0s - loss: 0.1000 - accuracy: 0.9849 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0911 - accuracy: 0.9861 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0874 - accuracy: 0.9861 - val_loss: 0.5754 - val_accuracy: 0.9252 Epoch 142/199 128/6993 [..............................] - ETA: 0s - loss: 0.0063 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0403 - accuracy: 0.9909 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0350 - accuracy: 0.9922 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0384 - accuracy: 0.9912 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0383 - accuracy: 0.9903 3328/6993 [=============>................] - ETA: 0s - loss: 0.0381 - accuracy: 0.9904 3968/6993 [================>.............] - ETA: 0s - loss: 0.0379 - accuracy: 0.9907 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0504 - accuracy: 0.9903 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0534 - accuracy: 0.9894 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0497 - accuracy: 0.9900 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0534 - accuracy: 0.9898 6912/6993 [============================>.] - ETA: 0s - loss: 0.0578 - accuracy: 0.9893 6993/6993 [==============================] - 1s 101us/sample - loss: 0.0572 - accuracy: 0.9894 - val_loss: 0.7234 - val_accuracy: 0.9151 Epoch 143/199 128/6993 [..............................] - ETA: 0s - loss: 0.0622 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.0633 - accuracy: 0.9844 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0875 - accuracy: 0.9826 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0650 - accuracy: 0.9862 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0552 - accuracy: 0.9885 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0546 - accuracy: 0.9890 3456/6993 [=============>................] - ETA: 0s - loss: 0.0566 - accuracy: 0.9864 4224/6993 [=================>............] - ETA: 0s - loss: 0.0721 - accuracy: 0.9853 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0727 - accuracy: 0.9854 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0684 - accuracy: 0.9858 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0673 - accuracy: 0.9858 6912/6993 [============================>.] - ETA: 0s - loss: 0.0651 - accuracy: 0.9861 6993/6993 [==============================] - 1s 95us/sample - loss: 0.0645 - accuracy: 0.9861 - val_loss: 0.6033 - val_accuracy: 0.9262 Epoch 144/199 128/6993 [..............................] - ETA: 0s - loss: 0.0339 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0727 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0499 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0532 - accuracy: 0.9888 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0494 - accuracy: 0.9891 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0522 - accuracy: 0.9883 4224/6993 [=================>............] - ETA: 0s - loss: 0.0580 - accuracy: 0.9882 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0644 - accuracy: 0.9864 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0649 - accuracy: 0.9860 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0693 - accuracy: 0.9860 6784/6993 [============================>.] - ETA: 0s - loss: 0.0703 - accuracy: 0.9858 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0701 - accuracy: 0.9858 - val_loss: 0.6120 - val_accuracy: 0.9262 Epoch 145/199 128/6993 [..............................] - ETA: 0s - loss: 0.0901 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0913 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0719 - accuracy: 0.9858 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0631 - accuracy: 0.9883 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0589 - accuracy: 0.9888 3328/6993 [=============>................] - ETA: 0s - loss: 0.0682 - accuracy: 0.9871 3968/6993 [================>.............] - ETA: 0s - loss: 0.0693 - accuracy: 0.9854 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0627 - accuracy: 0.9861 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0624 - accuracy: 0.9862 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0598 - accuracy: 0.9869 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0586 - accuracy: 0.9868 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0586 - accuracy: 0.9871 - val_loss: 0.6143 - val_accuracy: 0.9272 Epoch 146/199 128/6993 [..............................] - ETA: 0s - loss: 0.0308 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0400 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0421 - accuracy: 0.9893 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0439 - accuracy: 0.9873 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0412 - accuracy: 0.9892 3328/6993 [=============>................] - ETA: 0s - loss: 0.0419 - accuracy: 0.9904 3968/6993 [================>.............] - ETA: 0s - loss: 0.0433 - accuracy: 0.9899 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0538 - accuracy: 0.9887 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0598 - accuracy: 0.9876 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0612 - accuracy: 0.9878 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0591 - accuracy: 0.9877 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0580 - accuracy: 0.9878 - val_loss: 0.6531 - val_accuracy: 0.9226 Epoch 147/199 128/6993 [..............................] - ETA: 0s - loss: 0.0488 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.1087 - accuracy: 0.9805 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0884 - accuracy: 0.9851 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0766 - accuracy: 0.9863 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0712 - accuracy: 0.9870 3328/6993 [=============>................] - ETA: 0s - loss: 0.0748 - accuracy: 0.9874 3968/6993 [================>.............] - ETA: 0s - loss: 0.0787 - accuracy: 0.9864 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0741 - accuracy: 0.9872 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0734 - accuracy: 0.9860 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0781 - accuracy: 0.9859 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0732 - accuracy: 0.9863 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0705 - accuracy: 0.9867 - val_loss: 0.6328 - val_accuracy: 0.9287 Epoch 148/199 128/6993 [..............................] - ETA: 0s - loss: 0.1225 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.1028 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0773 - accuracy: 0.9908 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0607 - accuracy: 0.9907 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0540 - accuracy: 0.9901 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0581 - accuracy: 0.9884 4352/6993 [=================>............] - ETA: 0s - loss: 0.0823 - accuracy: 0.9869 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0735 - accuracy: 0.9880 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0695 - accuracy: 0.9883 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0698 - accuracy: 0.9886 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0670 - accuracy: 0.9884 - val_loss: 0.6386 - val_accuracy: 0.9363 Epoch 149/199 128/6993 [..............................] - ETA: 0s - loss: 0.0199 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1123 - accuracy: 0.9855 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0795 - accuracy: 0.9889 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0737 - accuracy: 0.9899 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0774 - accuracy: 0.9879 3456/6993 [=============>................] - ETA: 0s - loss: 0.0986 - accuracy: 0.9855 4096/6993 [================>.............] - ETA: 0s - loss: 0.0898 - accuracy: 0.9863 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0919 - accuracy: 0.9867 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0858 - accuracy: 0.9867 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0832 - accuracy: 0.9871 6784/6993 [============================>.] - ETA: 0s - loss: 0.0789 - accuracy: 0.9873 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0791 - accuracy: 0.9868 - val_loss: 0.6276 - val_accuracy: 0.9328 Epoch 150/199 128/6993 [..............................] - ETA: 0s - loss: 0.1339 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0890 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0948 - accuracy: 0.9851 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0975 - accuracy: 0.9839 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0806 - accuracy: 0.9855 3456/6993 [=============>................] - ETA: 0s - loss: 0.0802 - accuracy: 0.9847 4096/6993 [================>.............] - ETA: 0s - loss: 0.0789 - accuracy: 0.9856 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0848 - accuracy: 0.9844 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0801 - accuracy: 0.9844 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0809 - accuracy: 0.9852 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0798 - accuracy: 0.9850 - val_loss: 0.5406 - val_accuracy: 0.9262 Epoch 151/199 128/6993 [..............................] - ETA: 0s - loss: 0.0177 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0384 - accuracy: 0.9906 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0332 - accuracy: 0.9906 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0358 - accuracy: 0.9911 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0475 - accuracy: 0.9902 3072/6993 [============>.................] - ETA: 0s - loss: 0.0466 - accuracy: 0.9899 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0476 - accuracy: 0.9897 4096/6993 [================>.............] - ETA: 0s - loss: 0.0522 - accuracy: 0.9890 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0738 - accuracy: 0.9885 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0738 - accuracy: 0.9883 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0816 - accuracy: 0.9875 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0784 - accuracy: 0.9879 6784/6993 [============================>.] - ETA: 0s - loss: 0.0812 - accuracy: 0.9866 6993/6993 [==============================] - 1s 110us/sample - loss: 0.0795 - accuracy: 0.9866 - val_loss: 0.6048 - val_accuracy: 0.9277 Epoch 152/199 128/6993 [..............................] - ETA: 1s - loss: 0.0728 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0403 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0486 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0695 - accuracy: 0.9893 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0681 - accuracy: 0.9892 3328/6993 [=============>................] - ETA: 0s - loss: 0.0603 - accuracy: 0.9904 4096/6993 [================>.............] - ETA: 0s - loss: 0.0579 - accuracy: 0.9902 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0574 - accuracy: 0.9903 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0545 - accuracy: 0.9905 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0531 - accuracy: 0.9899 6784/6993 [============================>.] - ETA: 0s - loss: 0.0581 - accuracy: 0.9885 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0571 - accuracy: 0.9886 - val_loss: 0.5821 - val_accuracy: 0.9287 Epoch 153/199 128/6993 [..............................] - ETA: 1s - loss: 0.1013 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0793 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0767 - accuracy: 0.9822 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0666 - accuracy: 0.9824 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0678 - accuracy: 0.9836 3456/6993 [=============>................] - ETA: 0s - loss: 0.0689 - accuracy: 0.9835 4096/6993 [================>.............] - ETA: 0s - loss: 0.0756 - accuracy: 0.9836 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0769 - accuracy: 0.9829 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0764 - accuracy: 0.9829 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0757 - accuracy: 0.9832 6784/6993 [============================>.] - ETA: 0s - loss: 0.0760 - accuracy: 0.9836 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0752 - accuracy: 0.9834 - val_loss: 0.6578 - val_accuracy: 0.9262 Epoch 154/199 128/6993 [..............................] - ETA: 0s - loss: 0.1478 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.1026 - accuracy: 0.9792 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0721 - accuracy: 0.9837 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0590 - accuracy: 0.9871 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0592 - accuracy: 0.9883 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0647 - accuracy: 0.9886 4224/6993 [=================>............] - ETA: 0s - loss: 0.0630 - accuracy: 0.9884 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0634 - accuracy: 0.9882 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0617 - accuracy: 0.9889 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0646 - accuracy: 0.9884 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0634 - accuracy: 0.9886 - val_loss: 0.6112 - val_accuracy: 0.9282 Epoch 155/199 128/6993 [..............................] - ETA: 0s - loss: 0.1970 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0605 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0696 - accuracy: 0.9901 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0556 - accuracy: 0.9897 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0541 - accuracy: 0.9900 3328/6993 [=============>................] - ETA: 0s - loss: 0.0683 - accuracy: 0.9895 3968/6993 [================>.............] - ETA: 0s - loss: 0.0685 - accuracy: 0.9892 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0760 - accuracy: 0.9897 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0731 - accuracy: 0.9894 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0751 - accuracy: 0.9885 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0744 - accuracy: 0.9884 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0738 - accuracy: 0.9884 - val_loss: 0.5684 - val_accuracy: 0.9282 Epoch 156/199 128/6993 [..............................] - ETA: 0s - loss: 0.0023 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0568 - accuracy: 0.9896 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0615 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0812 - accuracy: 0.9863 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0885 - accuracy: 0.9862 3328/6993 [=============>................] - ETA: 0s - loss: 0.0837 - accuracy: 0.9850 3968/6993 [================>.............] - ETA: 0s - loss: 0.0790 - accuracy: 0.9849 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0722 - accuracy: 0.9865 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0804 - accuracy: 0.9865 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0798 - accuracy: 0.9856 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0789 - accuracy: 0.9852 6784/6993 [============================>.] - ETA: 0s - loss: 0.0774 - accuracy: 0.9856 6993/6993 [==============================] - 1s 99us/sample - loss: 0.0782 - accuracy: 0.9851 - val_loss: 0.5390 - val_accuracy: 0.9262 Epoch 157/199 128/6993 [..............................] - ETA: 0s - loss: 0.0985 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0669 - accuracy: 0.9883 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0525 - accuracy: 0.9898 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0498 - accuracy: 0.9917 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0612 - accuracy: 0.9910 3200/6993 [============>.................] - ETA: 0s - loss: 0.0608 - accuracy: 0.9909 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0708 - accuracy: 0.9898 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0655 - accuracy: 0.9902 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0682 - accuracy: 0.9901 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0632 - accuracy: 0.9900 6784/6993 [============================>.] - ETA: 0s - loss: 0.0654 - accuracy: 0.9892 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0643 - accuracy: 0.9891 - val_loss: 0.6331 - val_accuracy: 0.9181 Epoch 158/199 128/6993 [..............................] - ETA: 0s - loss: 0.0518 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0345 - accuracy: 0.9906 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0350 - accuracy: 0.9898 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0366 - accuracy: 0.9865 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0582 - accuracy: 0.9836 3328/6993 [=============>................] - ETA: 0s - loss: 0.0619 - accuracy: 0.9838 3968/6993 [================>.............] - ETA: 0s - loss: 0.0649 - accuracy: 0.9839 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0637 - accuracy: 0.9855 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0645 - accuracy: 0.9861 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0617 - accuracy: 0.9862 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0675 - accuracy: 0.9859 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0684 - accuracy: 0.9856 - val_loss: 0.5977 - val_accuracy: 0.9292 Epoch 159/199 128/6993 [..............................] - ETA: 0s - loss: 0.1453 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0490 - accuracy: 0.9883 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0658 - accuracy: 0.9844 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0566 - accuracy: 0.9862 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0697 - accuracy: 0.9869 3456/6993 [=============>................] - ETA: 0s - loss: 0.0753 - accuracy: 0.9867 4096/6993 [================>.............] - ETA: 0s - loss: 0.0917 - accuracy: 0.9846 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0880 - accuracy: 0.9846 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0896 - accuracy: 0.9849 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1116 - accuracy: 0.9840 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1086 - accuracy: 0.9842 6656/6993 [===========================>..] - ETA: 0s - loss: 0.1048 - accuracy: 0.9841 6993/6993 [==============================] - 1s 110us/sample - loss: 0.1008 - accuracy: 0.9844 - val_loss: 0.5150 - val_accuracy: 0.9302 Epoch 160/199 128/6993 [..............................] - ETA: 0s - loss: 0.0220 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0389 - accuracy: 0.9891 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0452 - accuracy: 0.9905 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0427 - accuracy: 0.9911 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0421 - accuracy: 0.9901 3200/6993 [============>.................] - ETA: 0s - loss: 0.0459 - accuracy: 0.9894 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0517 - accuracy: 0.9885 4352/6993 [=================>............] - ETA: 0s - loss: 0.0523 - accuracy: 0.9887 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0479 - accuracy: 0.9895 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0491 - accuracy: 0.9896 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0540 - accuracy: 0.9894 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0555 - accuracy: 0.9892 6993/6993 [==============================] - 1s 105us/sample - loss: 0.0613 - accuracy: 0.9893 - val_loss: 0.5710 - val_accuracy: 0.9292 Epoch 161/199 128/6993 [..............................] - ETA: 0s - loss: 0.0217 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0466 - accuracy: 0.9922 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0493 - accuracy: 0.9891 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0549 - accuracy: 0.9885 2560/6993 [=========>....................] - ETA: 0s - loss: 0.0508 - accuracy: 0.9891 3328/6993 [=============>................] - ETA: 0s - loss: 0.0444 - accuracy: 0.9898 3968/6993 [================>.............] - ETA: 0s - loss: 0.0505 - accuracy: 0.9892 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0524 - accuracy: 0.9887 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0593 - accuracy: 0.9880 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0668 - accuracy: 0.9875 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0657 - accuracy: 0.9878 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0670 - accuracy: 0.9877 - val_loss: 0.5431 - val_accuracy: 0.9317 Epoch 162/199 128/6993 [..............................] - ETA: 1s - loss: 0.0200 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0220 - accuracy: 0.9935 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0437 - accuracy: 0.9922 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0428 - accuracy: 0.9903 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0497 - accuracy: 0.9901 3456/6993 [=============>................] - ETA: 0s - loss: 0.0487 - accuracy: 0.9896 4096/6993 [================>.............] - ETA: 0s - loss: 0.0465 - accuracy: 0.9890 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0474 - accuracy: 0.9892 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0456 - accuracy: 0.9896 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0494 - accuracy: 0.9887 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0511 - accuracy: 0.9881 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0492 - accuracy: 0.9884 - val_loss: 0.5871 - val_accuracy: 0.9307 Epoch 163/199 128/6993 [..............................] - ETA: 0s - loss: 0.0673 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0430 - accuracy: 0.9875 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0439 - accuracy: 0.9891 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0409 - accuracy: 0.9901 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0489 - accuracy: 0.9900 3328/6993 [=============>................] - ETA: 0s - loss: 0.0486 - accuracy: 0.9895 3968/6993 [================>.............] - ETA: 0s - loss: 0.0487 - accuracy: 0.9899 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0588 - accuracy: 0.9883 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0619 - accuracy: 0.9878 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0604 - accuracy: 0.9874 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0593 - accuracy: 0.9874 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0609 - accuracy: 0.9874 - val_loss: 0.6339 - val_accuracy: 0.9267 Epoch 164/199 128/6993 [..............................] - ETA: 1s - loss: 0.1112 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0703 - accuracy: 0.9818 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0702 - accuracy: 0.9837 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0724 - accuracy: 0.9858 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0774 - accuracy: 0.9868 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0786 - accuracy: 0.9862 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0700 - accuracy: 0.9865 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0616 - accuracy: 0.9873 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0725 - accuracy: 0.9866 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0705 - accuracy: 0.9867 - val_loss: 0.7449 - val_accuracy: 0.9247 Epoch 165/199 128/6993 [..............................] - ETA: 0s - loss: 0.3661 - accuracy: 0.9766 896/6993 [==>...........................] - ETA: 0s - loss: 0.1344 - accuracy: 0.9810 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0875 - accuracy: 0.9857 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0724 - accuracy: 0.9871 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0616 - accuracy: 0.9886 3456/6993 [=============>................] - ETA: 0s - loss: 0.0547 - accuracy: 0.9887 4096/6993 [================>.............] - ETA: 0s - loss: 0.0493 - accuracy: 0.9902 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0453 - accuracy: 0.9907 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0606 - accuracy: 0.9896 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0618 - accuracy: 0.9884 6784/6993 [============================>.] - ETA: 0s - loss: 0.0638 - accuracy: 0.9882 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0630 - accuracy: 0.9884 - val_loss: 0.6633 - val_accuracy: 0.9282 Epoch 166/199 128/6993 [..............................] - ETA: 1s - loss: 0.1194 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1034 - accuracy: 0.9844 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0714 - accuracy: 0.9858 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0730 - accuracy: 0.9854 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0689 - accuracy: 0.9870 3328/6993 [=============>................] - ETA: 0s - loss: 0.0625 - accuracy: 0.9886 3968/6993 [================>.............] - ETA: 0s - loss: 0.0591 - accuracy: 0.9882 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0597 - accuracy: 0.9876 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0587 - accuracy: 0.9876 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0611 - accuracy: 0.9869 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0598 - accuracy: 0.9877 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0594 - accuracy: 0.9881 - val_loss: 0.6294 - val_accuracy: 0.9287 Epoch 167/199 128/6993 [..............................] - ETA: 0s - loss: 0.0474 - accuracy: 0.9844 640/6993 [=>............................] - ETA: 0s - loss: 0.2243 - accuracy: 0.9781 1280/6993 [====>.........................] - ETA: 0s - loss: 0.1350 - accuracy: 0.9820 1920/6993 [=======>......................] - ETA: 0s - loss: 0.1020 - accuracy: 0.9833 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1076 - accuracy: 0.9820 3200/6993 [============>.................] - ETA: 0s - loss: 0.0895 - accuracy: 0.9850 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0775 - accuracy: 0.9865 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0817 - accuracy: 0.9850 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0906 - accuracy: 0.9859 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0848 - accuracy: 0.9862 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0874 - accuracy: 0.9856 6993/6993 [==============================] - 1s 94us/sample - loss: 0.0854 - accuracy: 0.9858 - val_loss: 0.5833 - val_accuracy: 0.9237 Epoch 168/199 128/6993 [..............................] - ETA: 0s - loss: 0.1764 - accuracy: 0.9922 640/6993 [=>............................] - ETA: 0s - loss: 0.0904 - accuracy: 0.9906 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0876 - accuracy: 0.9913 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1010 - accuracy: 0.9874 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0914 - accuracy: 0.9881 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0928 - accuracy: 0.9859 3200/6993 [============>.................] - ETA: 0s - loss: 0.0937 - accuracy: 0.9856 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0901 - accuracy: 0.9863 4352/6993 [=================>............] - ETA: 0s - loss: 0.0879 - accuracy: 0.9860 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0826 - accuracy: 0.9860 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0842 - accuracy: 0.9862 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0938 - accuracy: 0.9854 6784/6993 [============================>.] - ETA: 0s - loss: 0.0911 - accuracy: 0.9856 6993/6993 [==============================] - 1s 110us/sample - loss: 0.0889 - accuracy: 0.9858 - val_loss: 0.6083 - val_accuracy: 0.9297 Epoch 169/199 128/6993 [..............................] - ETA: 0s - loss: 0.0058 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0417 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0470 - accuracy: 0.9915 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0502 - accuracy: 0.9912 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0547 - accuracy: 0.9903 3456/6993 [=============>................] - ETA: 0s - loss: 0.0868 - accuracy: 0.9887 4096/6993 [================>.............] - ETA: 0s - loss: 0.0893 - accuracy: 0.9883 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0860 - accuracy: 0.9878 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0788 - accuracy: 0.9881 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0769 - accuracy: 0.9880 6784/6993 [============================>.] - ETA: 0s - loss: 0.0808 - accuracy: 0.9876 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0825 - accuracy: 0.9873 - val_loss: 0.6123 - val_accuracy: 0.9317 Epoch 170/199 128/6993 [..............................] - ETA: 0s - loss: 0.0043 - accuracy: 1.0000 640/6993 [=>............................] - ETA: 0s - loss: 0.0493 - accuracy: 0.9844 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0318 - accuracy: 0.9898 1920/6993 [=======>......................] - ETA: 0s - loss: 0.0657 - accuracy: 0.9885 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0575 - accuracy: 0.9900 3328/6993 [=============>................] - ETA: 0s - loss: 0.0545 - accuracy: 0.9898 3968/6993 [================>.............] - ETA: 0s - loss: 0.0572 - accuracy: 0.9902 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0664 - accuracy: 0.9887 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0647 - accuracy: 0.9880 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0604 - accuracy: 0.9881 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0585 - accuracy: 0.9887 6993/6993 [==============================] - 1s 90us/sample - loss: 0.0656 - accuracy: 0.9876 - val_loss: 0.6228 - val_accuracy: 0.9297 Epoch 171/199 128/6993 [..............................] - ETA: 0s - loss: 0.0187 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.0379 - accuracy: 0.9922 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0594 - accuracy: 0.9889 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0722 - accuracy: 0.9867 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0747 - accuracy: 0.9872 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0658 - accuracy: 0.9877 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0646 - accuracy: 0.9868 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0664 - accuracy: 0.9867 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0677 - accuracy: 0.9859 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0752 - accuracy: 0.9850 6993/6993 [==============================] - 1s 91us/sample - loss: 0.0730 - accuracy: 0.9854 - val_loss: 0.5975 - val_accuracy: 0.9257 Epoch 172/199 128/6993 [..............................] - ETA: 0s - loss: 0.1194 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0702 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0521 - accuracy: 0.9879 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0455 - accuracy: 0.9888 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0641 - accuracy: 0.9877 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0836 - accuracy: 0.9872 4352/6993 [=================>............] - ETA: 0s - loss: 0.0766 - accuracy: 0.9878 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0744 - accuracy: 0.9873 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0715 - accuracy: 0.9875 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0682 - accuracy: 0.9881 6993/6993 [==============================] - 1s 88us/sample - loss: 0.0734 - accuracy: 0.9877 - val_loss: 0.5599 - val_accuracy: 0.9353 Epoch 173/199 128/6993 [..............................] - ETA: 1s - loss: 0.0278 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0601 - accuracy: 0.9855 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0677 - accuracy: 0.9862 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0583 - accuracy: 0.9874 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0556 - accuracy: 0.9881 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0588 - accuracy: 0.9884 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0614 - accuracy: 0.9875 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0612 - accuracy: 0.9871 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0614 - accuracy: 0.9872 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0627 - accuracy: 0.9870 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0611 - accuracy: 0.9871 - val_loss: 0.5202 - val_accuracy: 0.9307 Epoch 174/199 128/6993 [..............................] - ETA: 0s - loss: 0.0363 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0600 - accuracy: 0.9888 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0711 - accuracy: 0.9902 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0673 - accuracy: 0.9896 3072/6993 [============>.................] - ETA: 0s - loss: 0.0593 - accuracy: 0.9906 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0639 - accuracy: 0.9903 4352/6993 [=================>............] - ETA: 0s - loss: 0.0711 - accuracy: 0.9897 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0713 - accuracy: 0.9893 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0662 - accuracy: 0.9893 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0656 - accuracy: 0.9892 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0676 - accuracy: 0.9886 - val_loss: 0.6348 - val_accuracy: 0.9317 Epoch 175/199 128/6993 [..............................] - ETA: 0s - loss: 0.0899 - accuracy: 0.9844 768/6993 [==>...........................] - ETA: 0s - loss: 0.0585 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0495 - accuracy: 0.9922 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0559 - accuracy: 0.9927 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0634 - accuracy: 0.9900 3328/6993 [=============>................] - ETA: 0s - loss: 0.0807 - accuracy: 0.9892 4096/6993 [================>.............] - ETA: 0s - loss: 0.0857 - accuracy: 0.9873 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0804 - accuracy: 0.9875 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0726 - accuracy: 0.9883 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0694 - accuracy: 0.9880 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0691 - accuracy: 0.9877 - val_loss: 0.5609 - val_accuracy: 0.9333 Epoch 176/199 128/6993 [..............................] - ETA: 0s - loss: 0.0102 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0181 - accuracy: 0.9911 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0235 - accuracy: 0.9933 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0722 - accuracy: 0.9893 3072/6993 [============>.................] - ETA: 0s - loss: 0.0619 - accuracy: 0.9906 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0653 - accuracy: 0.9906 4352/6993 [=================>............] - ETA: 0s - loss: 0.0775 - accuracy: 0.9906 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0754 - accuracy: 0.9901 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0722 - accuracy: 0.9900 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0673 - accuracy: 0.9903 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0629 - accuracy: 0.9906 6993/6993 [==============================] - 1s 105us/sample - loss: 0.0581 - accuracy: 0.9911 - val_loss: 0.6584 - val_accuracy: 0.9302 Epoch 177/199 128/6993 [..............................] - ETA: 1s - loss: 0.2794 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.1283 - accuracy: 0.9812 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0784 - accuracy: 0.9883 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0947 - accuracy: 0.9878 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1059 - accuracy: 0.9877 3456/6993 [=============>................] - ETA: 0s - loss: 0.0959 - accuracy: 0.9878 4096/6993 [================>.............] - ETA: 0s - loss: 0.0889 - accuracy: 0.9883 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0849 - accuracy: 0.9884 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0830 - accuracy: 0.9883 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0825 - accuracy: 0.9880 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0785 - accuracy: 0.9884 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0769 - accuracy: 0.9886 - val_loss: 0.5919 - val_accuracy: 0.9343 Epoch 178/199 128/6993 [..............................] - ETA: 0s - loss: 0.0022 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0775 - accuracy: 0.9831 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0934 - accuracy: 0.9844 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0898 - accuracy: 0.9854 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0802 - accuracy: 0.9868 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0762 - accuracy: 0.9876 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0692 - accuracy: 0.9882 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0674 - accuracy: 0.9887 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0631 - accuracy: 0.9889 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0654 - accuracy: 0.9882 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0665 - accuracy: 0.9877 - val_loss: 0.6349 - val_accuracy: 0.9297 Epoch 179/199 128/6993 [..............................] - ETA: 0s - loss: 0.0499 - accuracy: 0.9844 896/6993 [==>...........................] - ETA: 0s - loss: 0.0655 - accuracy: 0.9833 1664/6993 [======>.......................] - ETA: 0s - loss: 0.0498 - accuracy: 0.9874 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0754 - accuracy: 0.9856 3328/6993 [=============>................] - ETA: 0s - loss: 0.0832 - accuracy: 0.9862 4096/6993 [================>.............] - ETA: 0s - loss: 0.0856 - accuracy: 0.9863 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0795 - accuracy: 0.9866 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0787 - accuracy: 0.9864 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0771 - accuracy: 0.9867 6784/6993 [============================>.] - ETA: 0s - loss: 0.0747 - accuracy: 0.9866 6993/6993 [==============================] - 1s 87us/sample - loss: 0.0739 - accuracy: 0.9866 - val_loss: 0.6218 - val_accuracy: 0.9206 Epoch 180/199 128/6993 [..............................] - ETA: 0s - loss: 0.0314 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1528 - accuracy: 0.9870 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1174 - accuracy: 0.9844 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1358 - accuracy: 0.9812 2816/6993 [===========>..................] - ETA: 0s - loss: 0.1252 - accuracy: 0.9819 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1092 - accuracy: 0.9821 4224/6993 [=================>............] - ETA: 0s - loss: 0.1026 - accuracy: 0.9832 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0915 - accuracy: 0.9846 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0909 - accuracy: 0.9846 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0840 - accuracy: 0.9855 6784/6993 [============================>.] - ETA: 0s - loss: 0.0803 - accuracy: 0.9858 6993/6993 [==============================] - 1s 86us/sample - loss: 0.0781 - accuracy: 0.9861 - val_loss: 0.6802 - val_accuracy: 0.9237 Epoch 181/199 128/6993 [..............................] - ETA: 0s - loss: 0.0131 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0772 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0742 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0622 - accuracy: 0.9902 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0778 - accuracy: 0.9893 3456/6993 [=============>................] - ETA: 0s - loss: 0.0807 - accuracy: 0.9884 4096/6993 [================>.............] - ETA: 0s - loss: 0.0759 - accuracy: 0.9890 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0698 - accuracy: 0.9897 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0682 - accuracy: 0.9892 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0681 - accuracy: 0.9892 6784/6993 [============================>.] - ETA: 0s - loss: 0.0857 - accuracy: 0.9875 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0840 - accuracy: 0.9873 - val_loss: 0.5772 - val_accuracy: 0.9252 Epoch 182/199 128/6993 [..............................] - ETA: 0s - loss: 0.0927 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0516 - accuracy: 0.9896 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0602 - accuracy: 0.9896 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0695 - accuracy: 0.9881 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0616 - accuracy: 0.9879 3456/6993 [=============>................] - ETA: 0s - loss: 0.0651 - accuracy: 0.9873 4096/6993 [================>.............] - ETA: 0s - loss: 0.0665 - accuracy: 0.9871 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0690 - accuracy: 0.9866 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0688 - accuracy: 0.9871 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0644 - accuracy: 0.9880 6784/6993 [============================>.] - ETA: 0s - loss: 0.0639 - accuracy: 0.9876 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0692 - accuracy: 0.9877 - val_loss: 0.5471 - val_accuracy: 0.9292 Epoch 183/199 128/6993 [..............................] - ETA: 0s - loss: 0.0696 - accuracy: 0.9688 640/6993 [=>............................] - ETA: 0s - loss: 0.1741 - accuracy: 0.9812 1152/6993 [===>..........................] - ETA: 0s - loss: 0.1318 - accuracy: 0.9870 1664/6993 [======>.......................] - ETA: 0s - loss: 0.1153 - accuracy: 0.9874 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0929 - accuracy: 0.9878 3072/6993 [============>.................] - ETA: 0s - loss: 0.0908 - accuracy: 0.9870 3968/6993 [================>.............] - ETA: 0s - loss: 0.0823 - accuracy: 0.9874 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0787 - accuracy: 0.9876 5248/6993 [=====================>........] - ETA: 0s - loss: 0.1121 - accuracy: 0.9874 5760/6993 [=======================>......] - ETA: 0s - loss: 0.1094 - accuracy: 0.9878 6272/6993 [=========================>....] - ETA: 0s - loss: 0.1139 - accuracy: 0.9866 6912/6993 [============================>.] - ETA: 0s - loss: 0.1130 - accuracy: 0.9860 6993/6993 [==============================] - 1s 99us/sample - loss: 0.1118 - accuracy: 0.9861 - val_loss: 0.6083 - val_accuracy: 0.9317 Epoch 184/199 128/6993 [..............................] - ETA: 0s - loss: 0.0105 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0299 - accuracy: 0.9909 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0419 - accuracy: 0.9893 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0605 - accuracy: 0.9873 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0799 - accuracy: 0.9859 3328/6993 [=============>................] - ETA: 0s - loss: 0.0807 - accuracy: 0.9853 3968/6993 [================>.............] - ETA: 0s - loss: 0.0847 - accuracy: 0.9856 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0807 - accuracy: 0.9852 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0733 - accuracy: 0.9857 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0801 - accuracy: 0.9862 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0760 - accuracy: 0.9865 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0731 - accuracy: 0.9868 - val_loss: 0.6655 - val_accuracy: 0.9272 Epoch 185/199 128/6993 [..............................] - ETA: 1s - loss: 0.0046 - accuracy: 1.0000 640/6993 [=>............................] - ETA: 0s - loss: 0.0538 - accuracy: 0.9875 1024/6993 [===>..........................] - ETA: 0s - loss: 0.0669 - accuracy: 0.9863 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0529 - accuracy: 0.9879 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0543 - accuracy: 0.9888 2304/6993 [========>.....................] - ETA: 0s - loss: 0.0589 - accuracy: 0.9891 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0648 - accuracy: 0.9881 3200/6993 [============>.................] - ETA: 0s - loss: 0.0787 - accuracy: 0.9878 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0782 - accuracy: 0.9876 4352/6993 [=================>............] - ETA: 0s - loss: 0.0703 - accuracy: 0.9885 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0706 - accuracy: 0.9877 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0665 - accuracy: 0.9885 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0623 - accuracy: 0.9884 6993/6993 [==============================] - 1s 116us/sample - loss: 0.0602 - accuracy: 0.9886 - val_loss: 0.7873 - val_accuracy: 0.9277 Epoch 186/199 128/6993 [..............................] - ETA: 0s - loss: 0.6546 - accuracy: 0.9609 896/6993 [==>...........................] - ETA: 0s - loss: 0.1723 - accuracy: 0.9877 1536/6993 [=====>........................] - ETA: 0s - loss: 0.1600 - accuracy: 0.9876 2176/6993 [========>.....................] - ETA: 0s - loss: 0.1197 - accuracy: 0.9885 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1023 - accuracy: 0.9888 3328/6993 [=============>................] - ETA: 0s - loss: 0.0991 - accuracy: 0.9886 3968/6993 [================>.............] - ETA: 0s - loss: 0.0871 - accuracy: 0.9892 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0857 - accuracy: 0.9881 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0806 - accuracy: 0.9884 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0737 - accuracy: 0.9893 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0737 - accuracy: 0.9893 6993/6993 [==============================] - 1s 96us/sample - loss: 0.0702 - accuracy: 0.9894 - val_loss: 0.7024 - val_accuracy: 0.9302 Epoch 187/199 128/6993 [..............................] - ETA: 0s - loss: 0.0199 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0181 - accuracy: 0.9961 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0526 - accuracy: 0.9922 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0519 - accuracy: 0.9922 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0517 - accuracy: 0.9911 3328/6993 [=============>................] - ETA: 0s - loss: 0.0652 - accuracy: 0.9916 4096/6993 [================>.............] - ETA: 0s - loss: 0.0677 - accuracy: 0.9910 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0618 - accuracy: 0.9913 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0605 - accuracy: 0.9911 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0608 - accuracy: 0.9906 6784/6993 [============================>.] - ETA: 0s - loss: 0.0649 - accuracy: 0.9898 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0696 - accuracy: 0.9896 - val_loss: 0.7536 - val_accuracy: 0.9287 Epoch 188/199 128/6993 [..............................] - ETA: 0s - loss: 3.0703e-04 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0303 - accuracy: 0.9922 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0205 - accuracy: 0.9943 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0305 - accuracy: 0.9937 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0365 - accuracy: 0.9926 3200/6993 [============>.................] - ETA: 0s - loss: 0.0357 - accuracy: 0.9928 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0318 - accuracy: 0.9935 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0455 - accuracy: 0.9922 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0527 - accuracy: 0.9916 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0614 - accuracy: 0.9907 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0572 - accuracy: 0.9910 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0557 - accuracy: 0.9908 - val_loss: 0.6957 - val_accuracy: 0.9317 Epoch 189/199 128/6993 [..............................] - ETA: 0s - loss: 0.0127 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.1007 - accuracy: 0.9870 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0861 - accuracy: 0.9886 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0890 - accuracy: 0.9868 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0832 - accuracy: 0.9881 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0903 - accuracy: 0.9872 4352/6993 [=================>............] - ETA: 0s - loss: 0.0963 - accuracy: 0.9862 4992/6993 [====================>.........] - ETA: 0s - loss: 0.0924 - accuracy: 0.9870 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0865 - accuracy: 0.9874 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0825 - accuracy: 0.9872 6912/6993 [============================>.] - ETA: 0s - loss: 0.0909 - accuracy: 0.9868 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0899 - accuracy: 0.9870 - val_loss: 0.6629 - val_accuracy: 0.9242 Epoch 190/199 128/6993 [..............................] - ETA: 0s - loss: 0.0112 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0707 - accuracy: 0.9857 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0645 - accuracy: 0.9876 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0812 - accuracy: 0.9871 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0760 - accuracy: 0.9879 3456/6993 [=============>................] - ETA: 0s - loss: 0.0684 - accuracy: 0.9881 4096/6993 [================>.............] - ETA: 0s - loss: 0.0635 - accuracy: 0.9885 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0749 - accuracy: 0.9880 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0765 - accuracy: 0.9875 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0768 - accuracy: 0.9873 6528/6993 [===========================>..] - ETA: 0s - loss: 0.0769 - accuracy: 0.9873 6993/6993 [==============================] - 1s 93us/sample - loss: 0.0751 - accuracy: 0.9876 - val_loss: 0.6277 - val_accuracy: 0.9302 Epoch 191/199 128/6993 [..............................] - ETA: 0s - loss: 0.0137 - accuracy: 1.0000 640/6993 [=>............................] - ETA: 0s - loss: 0.0647 - accuracy: 0.9875 1152/6993 [===>..........................] - ETA: 0s - loss: 0.0852 - accuracy: 0.9852 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0827 - accuracy: 0.9860 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0789 - accuracy: 0.9860 3072/6993 [============>.................] - ETA: 0s - loss: 0.0864 - accuracy: 0.9876 3712/6993 [==============>...............] - ETA: 0s - loss: 0.0819 - accuracy: 0.9876 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0707 - accuracy: 0.9886 5120/6993 [====================>.........] - ETA: 0s - loss: 0.0646 - accuracy: 0.9891 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0605 - accuracy: 0.9894 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0629 - accuracy: 0.9894 6993/6993 [==============================] - 1s 98us/sample - loss: 0.0623 - accuracy: 0.9894 - val_loss: 0.7846 - val_accuracy: 0.9226 Epoch 192/199 128/6993 [..............................] - ETA: 0s - loss: 0.0048 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0350 - accuracy: 0.9857 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0391 - accuracy: 0.9872 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0696 - accuracy: 0.9878 2688/6993 [==========>...................] - ETA: 0s - loss: 0.0716 - accuracy: 0.9866 3072/6993 [============>.................] - ETA: 0s - loss: 0.0695 - accuracy: 0.9873 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0645 - accuracy: 0.9880 4096/6993 [================>.............] - ETA: 0s - loss: 0.0593 - accuracy: 0.9888 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0532 - accuracy: 0.9893 5760/6993 [=======================>......] - ETA: 0s - loss: 0.0548 - accuracy: 0.9894 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0631 - accuracy: 0.9884 6993/6993 [==============================] - 1s 97us/sample - loss: 0.0640 - accuracy: 0.9886 - val_loss: 0.6628 - val_accuracy: 0.9302 Epoch 193/199 128/6993 [..............................] - ETA: 0s - loss: 0.0207 - accuracy: 1.0000 768/6993 [==>...........................] - ETA: 0s - loss: 0.0898 - accuracy: 0.9805 1280/6993 [====>.........................] - ETA: 0s - loss: 0.0944 - accuracy: 0.9844 1792/6993 [======>.......................] - ETA: 0s - loss: 0.0789 - accuracy: 0.9860 2432/6993 [=========>....................] - ETA: 0s - loss: 0.0938 - accuracy: 0.9848 2944/6993 [===========>..................] - ETA: 0s - loss: 0.0859 - accuracy: 0.9844 3584/6993 [==============>...............] - ETA: 0s - loss: 0.1096 - accuracy: 0.9838 4224/6993 [=================>............] - ETA: 0s - loss: 0.1132 - accuracy: 0.9851 4864/6993 [===================>..........] - ETA: 0s - loss: 0.1049 - accuracy: 0.9854 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0933 - accuracy: 0.9863 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0901 - accuracy: 0.9863 6912/6993 [============================>.] - ETA: 0s - loss: 0.0853 - accuracy: 0.9867 6993/6993 [==============================] - 1s 101us/sample - loss: 0.0852 - accuracy: 0.9864 - val_loss: 0.6907 - val_accuracy: 0.9317 Epoch 194/199 128/6993 [..............................] - ETA: 0s - loss: 0.0524 - accuracy: 0.9922 896/6993 [==>...........................] - ETA: 0s - loss: 0.1423 - accuracy: 0.9855 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1292 - accuracy: 0.9849 2560/6993 [=========>....................] - ETA: 0s - loss: 0.1021 - accuracy: 0.9867 3200/6993 [============>.................] - ETA: 0s - loss: 0.0939 - accuracy: 0.9859 3840/6993 [===============>..............] - ETA: 0s - loss: 0.0975 - accuracy: 0.9859 4480/6993 [==================>...........] - ETA: 0s - loss: 0.0932 - accuracy: 0.9866 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0879 - accuracy: 0.9870 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0822 - accuracy: 0.9877 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0795 - accuracy: 0.9882 6784/6993 [============================>.] - ETA: 0s - loss: 0.0834 - accuracy: 0.9881 6993/6993 [==============================] - 1s 101us/sample - loss: 0.0884 - accuracy: 0.9871 - val_loss: 0.5894 - val_accuracy: 0.9312 Epoch 195/199 128/6993 [..............................] - ETA: 0s - loss: 0.3211 - accuracy: 0.9766 640/6993 [=>............................] - ETA: 0s - loss: 0.2009 - accuracy: 0.9859 1152/6993 [===>..........................] - ETA: 0s - loss: 0.1260 - accuracy: 0.9887 1792/6993 [======>.......................] - ETA: 0s - loss: 0.1024 - accuracy: 0.9888 2432/6993 [=========>....................] - ETA: 0s - loss: 0.1080 - accuracy: 0.9893 3072/6993 [============>.................] - ETA: 0s - loss: 0.0948 - accuracy: 0.9896 3968/6993 [================>.............] - ETA: 0s - loss: 0.0936 - accuracy: 0.9889 4608/6993 [==================>...........] - ETA: 0s - loss: 0.0833 - accuracy: 0.9900 5248/6993 [=====================>........] - ETA: 0s - loss: 0.0762 - accuracy: 0.9903 5888/6993 [========================>.....] - ETA: 0s - loss: 0.0745 - accuracy: 0.9905 6400/6993 [==========================>...] - ETA: 0s - loss: 0.0717 - accuracy: 0.9905 6912/6993 [============================>.] - ETA: 0s - loss: 0.0718 - accuracy: 0.9902 6993/6993 [==============================] - 1s 100us/sample - loss: 0.0723 - accuracy: 0.9898 - val_loss: 0.6326 - val_accuracy: 0.9282 Epoch 196/199 128/6993 [..............................] - ETA: 0s - loss: 0.0088 - accuracy: 1.0000 896/6993 [==>...........................] - ETA: 0s - loss: 0.0504 - accuracy: 0.9922 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0660 - accuracy: 0.9909 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0529 - accuracy: 0.9908 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0484 - accuracy: 0.9908 3456/6993 [=============>................] - ETA: 0s - loss: 0.0772 - accuracy: 0.9902 4096/6993 [================>.............] - ETA: 0s - loss: 0.0791 - accuracy: 0.9905 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0758 - accuracy: 0.9903 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0708 - accuracy: 0.9903 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0672 - accuracy: 0.9902 6784/6993 [============================>.] - ETA: 0s - loss: 0.0627 - accuracy: 0.9907 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0696 - accuracy: 0.9904 - val_loss: 0.6836 - val_accuracy: 0.9312 Epoch 197/199 128/6993 [..............................] - ETA: 1s - loss: 0.2248 - accuracy: 0.9688 768/6993 [==>...........................] - ETA: 0s - loss: 0.1418 - accuracy: 0.9870 1408/6993 [=====>........................] - ETA: 0s - loss: 0.1008 - accuracy: 0.9886 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0902 - accuracy: 0.9903 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0750 - accuracy: 0.9904 3456/6993 [=============>................] - ETA: 0s - loss: 0.0683 - accuracy: 0.9893 4096/6993 [================>.............] - ETA: 0s - loss: 0.0654 - accuracy: 0.9883 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0720 - accuracy: 0.9875 5376/6993 [======================>.......] - ETA: 0s - loss: 0.0694 - accuracy: 0.9870 6016/6993 [========================>.....] - ETA: 0s - loss: 0.0686 - accuracy: 0.9869 6656/6993 [===========================>..] - ETA: 0s - loss: 0.0767 - accuracy: 0.9863 6993/6993 [==============================] - 1s 92us/sample - loss: 0.0770 - accuracy: 0.9858 - val_loss: 0.6915 - val_accuracy: 0.9267 Epoch 198/199 128/6993 [..............................] - ETA: 0s - loss: 0.1943 - accuracy: 0.9766 768/6993 [==>...........................] - ETA: 0s - loss: 0.0566 - accuracy: 0.9883 1408/6993 [=====>........................] - ETA: 0s - loss: 0.0769 - accuracy: 0.9879 2048/6993 [=======>......................] - ETA: 0s - loss: 0.0999 - accuracy: 0.9878 2688/6993 [==========>...................] - ETA: 0s - loss: 0.1052 - accuracy: 0.9870 3456/6993 [=============>................] - ETA: 0s - loss: 0.0932 - accuracy: 0.9881 4096/6993 [================>.............] - ETA: 0s - loss: 0.0833 - accuracy: 0.9883 4736/6993 [===================>..........] - ETA: 0s - loss: 0.0746 - accuracy: 0.9897 5504/6993 [======================>.......] - ETA: 0s - loss: 0.0780 - accuracy: 0.9900 6144/6993 [=========================>....] - ETA: 0s - loss: 0.0808 - accuracy: 0.9899 6784/6993 [============================>.] - ETA: 0s - loss: 0.0759 - accuracy: 0.9900 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0751 - accuracy: 0.9900 - val_loss: 0.6105 - val_accuracy: 0.9307 Epoch 199/199 128/6993 [..............................] - ETA: 0s - loss: 0.0453 - accuracy: 0.9922 768/6993 [==>...........................] - ETA: 0s - loss: 0.0957 - accuracy: 0.9870 1536/6993 [=====>........................] - ETA: 0s - loss: 0.0664 - accuracy: 0.9883 2176/6993 [========>.....................] - ETA: 0s - loss: 0.0841 - accuracy: 0.9853 2816/6993 [===========>..................] - ETA: 0s - loss: 0.0723 - accuracy: 0.9869 3584/6993 [==============>...............] - ETA: 0s - loss: 0.0741 - accuracy: 0.9858 4224/6993 [=================>............] - ETA: 0s - loss: 0.0641 - accuracy: 0.9877 4864/6993 [===================>..........] - ETA: 0s - loss: 0.0638 - accuracy: 0.9875 5632/6993 [=======================>......] - ETA: 0s - loss: 0.0594 - accuracy: 0.9874 6272/6993 [=========================>....] - ETA: 0s - loss: 0.0611 - accuracy: 0.9877 6912/6993 [============================>.] - ETA: 0s - loss: 0.0601 - accuracy: 0.9883 6993/6993 [==============================] - 1s 89us/sample - loss: 0.0612 - accuracy: 0.9883 - val_loss: 0.7666 - val_accuracy: 0.9247 Evaluating model for iteration 4... 1019/1019 - 0s - loss: 0.6855 - accuracy: 0.9313 Accuracy for iteration 4 0.9313052296638489
with open("logs/cnn1/eval_logs/cnn1_5.json") as f:
cnn1_log = json.load(f)
with open("logs/fcnn1/eval_logs/fcnn1_5.json") as f:
fcnn1_log = json.load(f)
with open("logs/fcnn2/eval_logs/fcnn2_5.json") as f:
fcnn2_log = json.load(f)
results_df = pd.DataFrame({"model":["cnn1", "fcnn1", "fcnn2"],
"accuracy":["{0:.2f}\u00B1 {1:.4f}".format(cnn1_log["mean_acc"], np.sqrt(cnn1_log["var_acc"])),
"{0:.2f}\u00B1 {1:.4f}".format(fcnn1_log["mean_acc"], np.sqrt(fcnn1_log["var_acc"])),
"{0:.2f}\u00B1 {1:.4f}".format(fcnn2_log["mean_acc"], np.sqrt(fcnn2_log["var_acc"]))]})
results_df
| model | accuracy | |
|---|---|---|
| 0 | cnn1 | 0.66± 0.0110 |
| 1 | fcnn1 | 0.89± 0.0087 |
| 2 | fcnn2 | 0.93± 0.0039 |
# Handy tool for converting results to LaTeX table.
print(results_df.to_latex(index=False))
\begin{tabular}{ll}
\toprule
model & accuracy \\
\midrule
cnn1 & 0.66± 0.0110 \\
fcnn1 & 0.89± 0.0087 \\
fcnn2 & 0.93± 0.0039 \\
\bottomrule
\end{tabular}